diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..6b057297bd700af674d66e78ea68598781a7f434 --- /dev/null +++ b/README.md @@ -0,0 +1,254 @@ +--- +license: llama3.1 +library_name: transformers +base_model: +- meta-llama/Llama-3.1-405B +pipeline_tag: text-generation +--- + +

+ Logo +

+ + +# Cogito v2 preview - 405B + +[Blog Post](https://www.deepcogito.com/research/cogito-v2-preview) + +The Cogito v2 LLMs are instruction tuned generative models. All models are released under an open license for commercial use. + +- Cogito v2 models are hybrid reasoning models. Each model can answer directly (standard LLM), or self-reflect before answering (like reasoning models). +- The LLMs are trained using **Iterated Distillation and Amplification (IDA)** - an scalable and efficient alignment strategy for superintelligence using iterative self-improvement. +- The models have been optimized for coding, STEM, instruction following and general helpfulness, and have significantly higher multilingual, coding and tool calling capabilities than size equivalent counterparts. + - In both standard and reasoning modes, Cogito v2-preview models outperform their size equivalent counterparts on common industry benchmarks. +- Each model is trained in over 30 languages and supports a context length of 128k. + +# Evaluations +For detailed evaluations, please refer to the [Blog Post](https://www.deepcogito.com/research/cogito-v2-preview). + + +# Usage +Here is a snippet below for usage with Transformers: + +```python +import transformers +import torch + +model_id = "deepcogito/cogito-v2-preview-llama-405B" + +pipeline = transformers.pipeline( + "text-generation", + model=model_id, + model_kwargs={"torch_dtype": torch.bfloat16}, + device_map="auto", +) + +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Give me a short introduction to LLMs."}, +] + +outputs = pipeline( + messages, + max_new_tokens=512, +) + +print(outputs[0]["generated_text"][-1]) +``` + + + +## Implementing extended thinking +- By default, the model will answer in the standard mode. +- To enable thinking, you can do any one of the two methods: + - Set `enable_thinking=True` while applying the chat template. + - Add a specific system prompt, along with prefilling the response with "\\n". + +**NOTE: Unlike Cogito v1 models, we initiate the response with "\\n" at the beginning of every output when reasoning is enabled. This is because hybrid models can be brittle at times (<0.1% of the cases), and adding a "\\n" ensures that the model does indeed respect thinking.** + +### Method 1 - Set enable_thinking=True in the tokenizer +If you are using Huggingface tokenizers, then you can simply use add the argument `enable_thinking=True` to the tokenization (this option is added to the chat template). + +Here is an example - +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "deepcogito/cogito-v2-preview-llama-405B" + +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto" +) +tokenizer = AutoTokenizer.from_pretrained(model_name) + +prompt = "Give me a short introduction to LLMs." +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": prompt} +] + +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, + enable_thinking=True +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +generated_ids = model.generate( + **model_inputs, + max_new_tokens=512 +) +generated_ids = [ + output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) +] + +response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] +print(response) +``` + +### Method 2 - Add a specific system prompt, along with prefilling the response with "\\n". +To enable thinking, you need to do two parts - + + +Step 1 - Simply use this in the system prompt `system_instruction = 'Enable deep thinking subroutine.'` + +If you already have a system_instruction, then use `system_instruction = 'Enable deep thinking subroutine.' + '\n\n' + system_instruction`. + +Step 2 - Prefil the response with the tokens `"\n"`. + +Here is an example - + +```python +import transformers +import torch + +model_name = "deepcogito/cogito-v2-preview-llama-405B" + +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto" +) +tokenizer = AutoTokenizer.from_pretrained(model_name) + +# Step 1 - Add deep thinking instruction. +DEEP_THINKING_INSTRUCTION = "Enable deep thinking subroutine." + +messages = [ + {"role": "system", "content": DEEP_THINKING_INSTRUCTION}, + {"role": "user", "content": "Write a bash script that takes a matrix represented as a string with format '[1,2],[3,4],[5,6]' and prints the transpose in the same format."}, +] + +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) + +# Step 2 - Prefill response with "\n". +text += "\n" + +# Now, continue as usual. +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +generated_ids = model.generate( + **model_inputs, + max_new_tokens=512 +) +generated_ids = [ + output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) +] + +response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] +print(response) +``` + + +Similarly, if you have a system prompt, you can append the `DEEP_THINKING_INSTRUCTION` to the beginning in this way - + +```python +DEEP_THINKING_INSTRUCTION = "Enable deep thinking subroutine." + +system_prompt = "Reply to each prompt with only the actual code - no explanations." +prompt = "Write a bash script that takes a matrix represented as a string with format '[1,2],[3,4],[5,6]' and prints the transpose in the same format." + +messages = [ + {"role": "system", "content": DEEP_THINKING_INSTRUCTION + '\n\n' + system_prompt}, + {"role": "user", "content": prompt} +] +``` + + +# Tool Calling +Cogito models support tool calling (single, parallel, multiple and parallel_multiple) both in standard and extended thinking mode. + +Here is a snippet - + +```python +# First, define a tool +def get_current_temperature(location: str) -> float: + """ + Get the current temperature at a location. + + Args: + location: The location to get the temperature for, in the format "City, Country" + Returns: + The current temperature at the specified location in the specified units, as a float. + """ + return 22. # A real function should probably actually get the temperature! + +# Next, create a chat and apply the chat template +messages = [ + {"role": "user", "content": "Hey, what's the temperature in Paris right now?"} +] + +model_inputs = tokenizer.apply_chat_template(messages, tools=[get_current_temperature], add_generation_prompt=True) + +text = tokenizer.apply_chat_template(messages, tools=[get_current_temperature], add_generation_prompt=True, tokenize=False) +inputs = tokenizer(text, return_tensors="pt", add_special_tokens=False).to(model.device) +outputs = model.generate(**inputs, max_new_tokens=512) +output_text = tokenizer.batch_decode(outputs)[0][len(text):] +print(output_text) +``` + +This will result in the output - +``` + +{"name": "get_current_temperature", "arguments": {"location": "Paris, France"}} +<|eot_id|> +``` + +You can then generate text from this input as normal. If the model generates a tool call, you should add it to the chat like so: + +```python +tool_call = {"name": "get_current_temperature", "arguments": {"location": "Paris, France"}} +messages.append({"role": "assistant", "tool_calls": [{"type": "function", "function": tool_call}]}) +``` + +and then call the tool and append the result, with the `tool` role, like so: + +```python +messages.append({"role": "tool", "name": "get_current_temperature", "content": "22.0"}) +``` + +After that, you can `generate()` again to let the model use the tool result in the chat: + +```python +text = tokenizer.apply_chat_template(messages, tools=[get_current_temperature], add_generation_prompt=True, tokenize=False) +inputs = tokenizer(text, return_tensors="pt", add_special_tokens=False).to(model.device) +outputs = model.generate(**inputs, max_new_tokens=512) +output_text = tokenizer.batch_decode(outputs)[0][len(text):] +``` + +This should result in the string - +``` +'The current temperature in Paris is 22.0 degrees.<|eot_id|>' +``` + +## License +This repository and the model weights are licensed under the [Llama 3.3 Community License Agreement](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE) (Llama models' default license agreement). + +## Contact +If you would like to reach out to our team, send an email to [contact@deepcogito.com](contact@deepcogito.com). diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..55dbce59ab4b279c6ba3a91777712dbb9e295cc0 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,123 @@ +{{- bos_token }} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} +{%- if not enable_thinking is defined %} + {%- set enable_thinking = false %} +{%- endif %} +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} +{#- Set the system message. If enable_thinking is true, add the "Enable deep thinking subroutine." #} +{%- if enable_thinking %} + {%- if system_message != "" %} + {%- set system_message = "Enable deep thinking subroutine. + +" ~ system_message %} + {%- else %} + {%- set system_message = "Enable deep thinking subroutine." %} + {%- endif %} +{%- endif %} +{#- Set the system message. In case there are tools present, add them to the system message. #} +{%- if tools is not none or system_message != '' %} + {{- "<|start_header_id|>system<|end_header_id|> + +" }} + {{- system_message }} + {%- if tools is not none %} + {%- if system_message != "" %} + {{- " + +" }} + {%- endif %} + {{- "Available Tools: +" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- " + +" }} + {%- endfor %} + {%- endif %} + {{- "<|eot_id|>" }} +{%- endif %} + +{#- Rest of the messages #} +{%- for message in messages %} + {#- The special cases are when the message is from a tool (via role ipython/tool/tool_results) or when the message is from the assistant, but has "tool_calls". If not, we add the message directly as usual. #} + {#- Case 1 - Usual, non tool related message. #} + {%- if not (message.role == "ipython" or message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|> + +' }} + {%- if message['content'] is string %} + {{- message['content'] | trim }} + {%- else %} + {%- for item in message['content'] %} + {%- if item.type == 'text' %} + {{- item.text | trim }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|eot_id|>' }} + + {#- Case 2 - the response is from the assistant, but has a tool call returned. The assistant may also have returned some content along with the tool call. #} + {%- elif message.tool_calls is defined and message.tool_calls is not none %} + {{- "<|start_header_id|>assistant<|end_header_id|> + +" }} + {%- if message['content'] is string %} + {{- message['content'] | trim }} + {%- else %} + {%- for item in message['content'] %} + {%- if item.type == 'text' %} + {{- item.text | trim }} + {%- if item.text | trim != "" %} + {{- " + +" }} + {%- endif %} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- "[" }} + {%- for tool_call in message.tool_calls %} + {%- set out = tool_call.function|tojson %} + {%- if not tool_call.id is defined %} + {{- out }} + {%- else %} + {{- out[:-1] }} + {{- ', "id": "' + tool_call.id + '"}' }} + {%- endif %} + {%- if not loop.last %} + {{- ", " }} + {%- else %} + {{- "]<|eot_id|>" }} + {%- endif %} + {%- endfor %} + + {#- Case 3 - the response is from a tool call. The tool call may have an id associated with it as well. If it does, we add it to the prompt. #} + {%- elif message.role == "ipython" or message["role"] == "tool_results" or message["role"] == "tool" %} + {{- "<|start_header_id|>ipython<|end_header_id|> + +" }} + {%- if message.tool_call_id is defined and message.tool_call_id != '' %} + {{- '{"content": ' + (message.content | tojson) + ', "call_id": "' + message.tool_call_id + '"}' }} + {%- else %} + {{- '{"content": ' + (message.content | tojson) + '}' }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|> + +' }} + {%- if enable_thinking %} + {{- '\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..14427e42ddbf74021cfe713049cd03a90f6ded04 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 16384, + "initializer_range": 0.02, + "intermediate_size": 53248, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 128, + "num_hidden_layers": 126, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.53.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/model-00006-of-00191.safetensors b/model-00006-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39773b0cc9dc1a403f90b2f45262a3d835b22efb --- /dev/null +++ b/model-00006-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7117f7539c3e627aa56c26436de62cafd82b75abd058e097bc7b1207c7e664 +size 3489661200 diff --git a/model-00012-of-00191.safetensors b/model-00012-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f33790d1e50a89de92b593283ba4666b845b3a32 --- /dev/null +++ b/model-00012-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366926d3047c0bacd272ed15c55ce86be399cf99dba82f0eb302b588ce3f747f +size 3489661200 diff --git a/model-00030-of-00191.safetensors b/model-00030-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2d967b8d75f8c71206dabbacadfca8f147036fb --- /dev/null +++ b/model-00030-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672f353bbdabbac38030b599f352dd54f3bc5a60582d1d6849e5f41cba6651e5 +size 3489661200 diff --git a/model-00033-of-00191.safetensors b/model-00033-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5241a0a7ec0eb2678d70dee90f5c11fc7ed6f42d --- /dev/null +++ b/model-00033-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea0e4d1677e17bdb346d43621098849236f0bfd96461ca75a5b7fb419a6f01b1 +size 3489661200 diff --git a/model-00039-of-00191.safetensors b/model-00039-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f0e51fbc5fc3c9465a54898bb1c883bb548c994 --- /dev/null +++ b/model-00039-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c23206fa7c9c051ed121b4031b7c78b33d3f29c9828e783013ac24652ea547e +size 3489661200 diff --git a/model-00042-of-00191.safetensors b/model-00042-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7df1b9d5f571dbd5ad7a9c608885bac6c3efe495 --- /dev/null +++ b/model-00042-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088b827b5beb35b1d61c38156695db8ee2063250beeaaa390a139f48142dab4c +size 3489661200 diff --git a/model-00048-of-00191.safetensors b/model-00048-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2a272c19b84b63a042f5b1353cca23802a11f46 --- /dev/null +++ b/model-00048-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b9cd930abd74e1da8237b8762c362391dbb90dc00712c1b186d1a1e8fdecaf +size 3489661200 diff --git a/model-00057-of-00191.safetensors b/model-00057-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80ce6ec33658cd1e0cd9ea4af658f3556d8f600b --- /dev/null +++ b/model-00057-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0cedacbedaf03c0bbfca01ad3076f7a20c555e404398787c127cba66471bf90 +size 3489661200 diff --git a/model-00063-of-00191.safetensors b/model-00063-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cfeb1d57919e0eb5737ed78c7f15c6f73965184c --- /dev/null +++ b/model-00063-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c72cd81f417104b40b3c098b4c58e9fb82cffc52b3f3a9a8b9a1cd1f8af7fa3 +size 3489661200 diff --git a/model-00069-of-00191.safetensors b/model-00069-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50dd88fe2612a05814d5323468506c885f13317f --- /dev/null +++ b/model-00069-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cee12d9e2223e2b3f8db76e9ccb19e9d7cadfaf09b1a0fbfae0216f0de771d5 +size 3489661200 diff --git a/model-00078-of-00191.safetensors b/model-00078-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..403909ba1664f8599dd3c12cf18470e42e60d339 --- /dev/null +++ b/model-00078-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3435994ba0c2586db36bb2085c0a3b30c9e4da694dc0e628ef7bd190f09a617 +size 3489661200 diff --git a/model-00081-of-00191.safetensors b/model-00081-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b09880a640a2c7c671b6dfc7256c2dd51d751f93 --- /dev/null +++ b/model-00081-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb275a89b0f511f20b00842c336724847466128269d46ea6d556f992e5751128 +size 3489661200 diff --git a/model-00087-of-00191.safetensors b/model-00087-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..673cd36754104b391b7127a8ea4c12f0f4498571 --- /dev/null +++ b/model-00087-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4ea6d4e911f073449503ab7fef80b5ac1e113bddbb751642116e43a65b7a32 +size 3489661200 diff --git a/model-00090-of-00191.safetensors b/model-00090-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ecf678e12a94fba43068df2904fc674b4e1c1bd4 --- /dev/null +++ b/model-00090-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1b52d143846566e17811061e183859c87390b1c8821ec8f2d5f370faf9337c5 +size 3489661200 diff --git a/model-00096-of-00191.safetensors b/model-00096-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39087b6a84d3da9722390aa0614f6a991062fa50 --- /dev/null +++ b/model-00096-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bf962497af1c2b721be44e91b8784d4eea01c64ee59424cd17272ab7623583f +size 3489661200 diff --git a/model-00099-of-00191.safetensors b/model-00099-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9896c569bace6277d3e1f3648d882a17c2694688 --- /dev/null +++ b/model-00099-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98449d4c280c56da4f40cb2ec29ae38c8f631e0bf814aff5e5a09028a0f909d8 +size 3489661200 diff --git a/model-00102-of-00191.safetensors b/model-00102-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d9336a8a38af146efc5a3e931df6c68515aef75 --- /dev/null +++ b/model-00102-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30aaaf067d24c655846938a1b54e317df54e36fe0ee8ad7c69bfd8d0fd3dede9 +size 3489661200 diff --git a/model-00105-of-00191.safetensors b/model-00105-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5dc2f02c1a832b96cadb7d359e70e5f1edbb3fa --- /dev/null +++ b/model-00105-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd0f94ae6eabb560103a4dc4d1f6013a0611be27d041c36ef3ba9efcbfa7fb2 +size 3489661200 diff --git a/model-00108-of-00191.safetensors b/model-00108-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51be17f5a64ec4b2b74a551fe13a9cac3db6d0bb --- /dev/null +++ b/model-00108-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7abc40730a2ed0acc7f1cfc7a6a06f22c5999713f1ea77f2795ed15db0c2bfc3 +size 3489661200 diff --git a/model-00111-of-00191.safetensors b/model-00111-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0a9a70444dd413838e8bbbfe0744c92aabe34a0 --- /dev/null +++ b/model-00111-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72a0159bf0c0155a133d18a6069a6a66b44e5296e7000d9d8f54a1cfa2dd35d +size 3489661200 diff --git a/model-00117-of-00191.safetensors b/model-00117-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bdc60eda27ac4922bed198f7aa0415c25c6d9b7b --- /dev/null +++ b/model-00117-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9751d1d3e7217dd30b45aa533c3776c3c0644e89e13c9a6c51a80bed75f30e94 +size 3489661200 diff --git a/model-00120-of-00191.safetensors b/model-00120-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ace639dc6b87ee2b024570d551433a8b73f97b35 --- /dev/null +++ b/model-00120-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c95330f5dd9976868dd40599d5a79a4f892fccb442612303eacee71e02ab3d9c +size 3489661200 diff --git a/model-00123-of-00191.safetensors b/model-00123-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e080a8911c5fe76c376d0896a752f1e287c0b0f8 --- /dev/null +++ b/model-00123-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640f7bb25eb6b1d3cc2b5bbd06b040014c4a6a96dd72c201e671fe768450e5c7 +size 3489661200 diff --git a/model-00126-of-00191.safetensors b/model-00126-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52d175fb76974f26e14cf9706fc66b7270cd3bb5 --- /dev/null +++ b/model-00126-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1b35c41fa07fe5ad203e5d3b81cbf38b1ebe359ce62acad16d8a3ed0f67e43f +size 3489661192 diff --git a/model-00129-of-00191.safetensors b/model-00129-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a9339bd39a04156d452b0f74a2295f9e9debb79a --- /dev/null +++ b/model-00129-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf6a816a53a0f1372d526d6fef5966ef09662993b04bdd81b58ce01e4f08d0e +size 3489661200 diff --git a/model-00132-of-00191.safetensors b/model-00132-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3a65809128894a348e52781e0c862607ac542a5 --- /dev/null +++ b/model-00132-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458d060d7d2160bd50baa0575747ff78f9d15640d7f1ef0c67fc98e464b4e5b1 +size 3489661200 diff --git a/model-00138-of-00191.safetensors b/model-00138-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c5d2fc33fcd84d350519be15be44ecbe0bcb0fd --- /dev/null +++ b/model-00138-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b9c644d7e4f8ac6d0806555d2678c2df7503efcd7c82e3a403084d1e185395 +size 3489661200 diff --git a/model-00141-of-00191.safetensors b/model-00141-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bde40e60319dacf512d21411448540321b045386 --- /dev/null +++ b/model-00141-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b6c462d7dfbc7035ce31f10bdf9c675307836f3cb7238bcbf78d619f34ca2d +size 3489661200 diff --git a/model-00144-of-00191.safetensors b/model-00144-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe934a3985c6f44c4444880f4d58d25002391548 --- /dev/null +++ b/model-00144-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82a2c0b7cc1c9bb5335578f599ed260dd3f4bf0d364deceecbd602eb08b74282 +size 3489661200 diff --git a/model-00147-of-00191.safetensors b/model-00147-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46010c7b4ef8920e8908a15b7e4ece8b3f16fbb5 --- /dev/null +++ b/model-00147-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2f70b9f1aea9551ada5446df65c5668fa7d2949d6e772e6cc7000a299a8993 +size 3489661200 diff --git a/model-00150-of-00191.safetensors b/model-00150-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7be9a1ba62b44f0ac11a33d7390466e87d5cbcd --- /dev/null +++ b/model-00150-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a43b92cce9890fd1e40849e279faab00e2f9f28f7f0ba140a8808ba16db473 +size 3489661200 diff --git a/model-00153-of-00191.safetensors b/model-00153-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d6101b4124073923ccf779efdc987a757c73cdb --- /dev/null +++ b/model-00153-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:055a988171dfde7121206f3e65419a577edc167452a17e4c75af2f34d2c8131a +size 3489661200 diff --git a/model-00156-of-00191.safetensors b/model-00156-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a834c4d291fe71bf467d352c25bd649599f44caf --- /dev/null +++ b/model-00156-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80ea7e7bcac3b57828ca433a411edfabbd0a48b3d7c8383638b8b6683fb1bdb +size 3489661200 diff --git a/model-00159-of-00191.safetensors b/model-00159-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e3e97a8055c8ea42c85cfc9149ba3cbb1cdd3ef5 --- /dev/null +++ b/model-00159-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37965d49f4206b790f491f63b74eca59daaeef42b12bf24cf8179e0e5a42ddd8 +size 3489661192 diff --git a/model-00162-of-00191.safetensors b/model-00162-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d44f301d5a3b08b9200fe55ac394619df4d6d764 --- /dev/null +++ b/model-00162-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6d6c1ec27f3bc8fddb918ce7126a6514f2f52326d10cacd8a6938b3ca3f1a5 +size 3489661200 diff --git a/model-00165-of-00191.safetensors b/model-00165-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa2c32fde4c7265aec74ce83831b0c81b149b800 --- /dev/null +++ b/model-00165-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3628daf1f504e7c2ba3872193f722b866245aef998db5dc83a4d4a1345efaf4a +size 3489661200 diff --git a/model-00168-of-00191.safetensors b/model-00168-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30f99954f862a4b33100bcb69087cd6a961bb9e3 --- /dev/null +++ b/model-00168-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311eed7129fe27a252ca6e0f5fe36df8f7e7c4fc001e7f6ea737c30247cf8130 +size 3489661200 diff --git a/model-00174-of-00191.safetensors b/model-00174-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..61786ca479df5468359bcaab920ae11aa9fcd758 --- /dev/null +++ b/model-00174-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7963a6897f738f815434a818445c0d84770a62215d5c41ac883d9f4e5c9e2307 +size 3489661200 diff --git a/model-00177-of-00191.safetensors b/model-00177-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b25b711791fb179477785d4099be1d86a42691c --- /dev/null +++ b/model-00177-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea750cc111f6ea1ef6091aca7e20fd6297266a2d5a8bbc389cb9f298d1962db +size 3489661200 diff --git a/model-00180-of-00191.safetensors b/model-00180-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6d4cc92232350ed99b2420dd3761d06e4f8cfa3 --- /dev/null +++ b/model-00180-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272929b0b3d7bc3b3ff0ee7a34b3f9fb142d72ace921a3f2f1d581eac56622e1 +size 3489661200 diff --git a/model-00183-of-00191.safetensors b/model-00183-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e8a619c8c701b61db01b280a01f334415f1eb9a --- /dev/null +++ b/model-00183-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7ea3fc49b7d231fb5d4f6614fb592d79af05f29da05a843d9c02e93b708a57 +size 3489661200 diff --git a/model-00186-of-00191.safetensors b/model-00186-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..274e082b46eab9592e429c1abfd2e00d154551a1 --- /dev/null +++ b/model-00186-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fddb9f771a82e55b50609d3f89cd30349d98c662b58c3b0fe0433db3142ef46 +size 3489661200 diff --git a/model-00189-of-00191.safetensors b/model-00189-of-00191.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c05b70e415310756ad2f752ef0e78779975e7af --- /dev/null +++ b/model-00189-of-00191.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ad6a84f4eb63d8120efc7859208c5226575c81854795dc97e6a9db072fa704 +size 3489661200 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..c7787a22572ed115dae4471403e6571f97350737 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"weight_map": {"lm_head.weight": "model-00001-of-00191.safetensors", "model.embed_tokens.weight": "model-00002-of-00191.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00191.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00191.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00191.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00191.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00191.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00191.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00191.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00191.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00191.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00191.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00191.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00191.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00191.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00191.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00191.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00191.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00191.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00191.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00191.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00191.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00191.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00191.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00191.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00191.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00191.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00191.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00191.safetensors", "model.layers.100.input_layernorm.weight": "model-00007-of-00191.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00007-of-00191.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00008-of-00191.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00008-of-00191.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00008-of-00191.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00008-of-00191.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00008-of-00191.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00008-of-00191.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00008-of-00191.safetensors", "model.layers.101.input_layernorm.weight": "model-00008-of-00191.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00009-of-00191.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00009-of-00191.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00010-of-00191.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00010-of-00191.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00010-of-00191.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00010-of-00191.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00010-of-00191.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00010-of-00191.safetensors", "model.layers.102.input_layernorm.weight": "model-00010-of-00191.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00010-of-00191.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00011-of-00191.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00011-of-00191.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00011-of-00191.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00011-of-00191.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00011-of-00191.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00011-of-00191.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00011-of-00191.safetensors", "model.layers.103.input_layernorm.weight": "model-00011-of-00191.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00012-of-00191.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00012-of-00191.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00013-of-00191.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00013-of-00191.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00013-of-00191.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00013-of-00191.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00013-of-00191.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00013-of-00191.safetensors", "model.layers.104.input_layernorm.weight": "model-00013-of-00191.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00013-of-00191.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00014-of-00191.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00014-of-00191.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00014-of-00191.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00014-of-00191.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00014-of-00191.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00014-of-00191.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00014-of-00191.safetensors", "model.layers.105.input_layernorm.weight": "model-00014-of-00191.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00015-of-00191.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00015-of-00191.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00016-of-00191.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00016-of-00191.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00016-of-00191.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00016-of-00191.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00016-of-00191.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00016-of-00191.safetensors", "model.layers.106.input_layernorm.weight": "model-00016-of-00191.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00016-of-00191.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00017-of-00191.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00017-of-00191.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00017-of-00191.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00017-of-00191.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00017-of-00191.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00017-of-00191.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00017-of-00191.safetensors", "model.layers.107.input_layernorm.weight": "model-00017-of-00191.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00018-of-00191.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00018-of-00191.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00019-of-00191.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00019-of-00191.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00019-of-00191.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00019-of-00191.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00019-of-00191.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00019-of-00191.safetensors", "model.layers.108.input_layernorm.weight": "model-00019-of-00191.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00019-of-00191.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00020-of-00191.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00020-of-00191.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00020-of-00191.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00020-of-00191.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00020-of-00191.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00020-of-00191.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00020-of-00191.safetensors", "model.layers.109.input_layernorm.weight": "model-00020-of-00191.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00021-of-00191.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00021-of-00191.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00022-of-00191.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00022-of-00191.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00022-of-00191.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00022-of-00191.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00022-of-00191.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00022-of-00191.safetensors", "model.layers.11.input_layernorm.weight": "model-00022-of-00191.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00022-of-00191.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00023-of-00191.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00023-of-00191.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00023-of-00191.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00023-of-00191.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00023-of-00191.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00023-of-00191.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00023-of-00191.safetensors", "model.layers.110.input_layernorm.weight": "model-00023-of-00191.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00024-of-00191.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00024-of-00191.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00025-of-00191.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00025-of-00191.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00025-of-00191.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00025-of-00191.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00025-of-00191.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00025-of-00191.safetensors", "model.layers.111.input_layernorm.weight": "model-00025-of-00191.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00025-of-00191.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00026-of-00191.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00026-of-00191.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00026-of-00191.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00026-of-00191.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00026-of-00191.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00026-of-00191.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00026-of-00191.safetensors", "model.layers.112.input_layernorm.weight": "model-00026-of-00191.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00027-of-00191.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00027-of-00191.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00028-of-00191.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00028-of-00191.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00028-of-00191.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00028-of-00191.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00028-of-00191.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00028-of-00191.safetensors", "model.layers.113.input_layernorm.weight": "model-00028-of-00191.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00028-of-00191.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00029-of-00191.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00029-of-00191.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00029-of-00191.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00029-of-00191.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00029-of-00191.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00029-of-00191.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00029-of-00191.safetensors", "model.layers.114.input_layernorm.weight": "model-00029-of-00191.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00030-of-00191.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00030-of-00191.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00031-of-00191.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00031-of-00191.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00031-of-00191.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00031-of-00191.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00031-of-00191.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00031-of-00191.safetensors", "model.layers.115.input_layernorm.weight": "model-00031-of-00191.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00031-of-00191.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00032-of-00191.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00032-of-00191.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00032-of-00191.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00032-of-00191.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00032-of-00191.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00032-of-00191.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00032-of-00191.safetensors", "model.layers.116.input_layernorm.weight": "model-00032-of-00191.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00033-of-00191.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00033-of-00191.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00034-of-00191.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00034-of-00191.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00034-of-00191.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00034-of-00191.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00034-of-00191.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00034-of-00191.safetensors", "model.layers.117.input_layernorm.weight": "model-00034-of-00191.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00034-of-00191.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00035-of-00191.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00035-of-00191.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00035-of-00191.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00035-of-00191.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00035-of-00191.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00035-of-00191.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00035-of-00191.safetensors", "model.layers.118.input_layernorm.weight": "model-00035-of-00191.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00036-of-00191.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00036-of-00191.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00037-of-00191.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00037-of-00191.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00037-of-00191.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00037-of-00191.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00037-of-00191.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00037-of-00191.safetensors", "model.layers.119.input_layernorm.weight": "model-00037-of-00191.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00037-of-00191.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00038-of-00191.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00038-of-00191.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00038-of-00191.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00038-of-00191.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00038-of-00191.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00038-of-00191.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00038-of-00191.safetensors", "model.layers.12.input_layernorm.weight": "model-00038-of-00191.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00039-of-00191.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00039-of-00191.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00040-of-00191.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00040-of-00191.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00040-of-00191.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00040-of-00191.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00040-of-00191.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00040-of-00191.safetensors", "model.layers.120.input_layernorm.weight": "model-00040-of-00191.safetensors", "model.layers.120.mlp.down_proj.weight": "model-00040-of-00191.safetensors", "model.layers.120.mlp.gate_proj.weight": "model-00041-of-00191.safetensors", "model.layers.120.mlp.up_proj.weight": "model-00041-of-00191.safetensors", "model.layers.120.post_attention_layernorm.weight": "model-00041-of-00191.safetensors", "model.layers.120.self_attn.k_proj.weight": "model-00041-of-00191.safetensors", "model.layers.120.self_attn.o_proj.weight": "model-00041-of-00191.safetensors", "model.layers.120.self_attn.q_proj.weight": "model-00041-of-00191.safetensors", "model.layers.120.self_attn.v_proj.weight": "model-00041-of-00191.safetensors", "model.layers.121.input_layernorm.weight": "model-00041-of-00191.safetensors", "model.layers.121.mlp.down_proj.weight": "model-00042-of-00191.safetensors", "model.layers.121.mlp.gate_proj.weight": "model-00042-of-00191.safetensors", "model.layers.121.mlp.up_proj.weight": "model-00043-of-00191.safetensors", "model.layers.121.post_attention_layernorm.weight": "model-00043-of-00191.safetensors", "model.layers.121.self_attn.k_proj.weight": "model-00043-of-00191.safetensors", "model.layers.121.self_attn.o_proj.weight": "model-00043-of-00191.safetensors", "model.layers.121.self_attn.q_proj.weight": "model-00043-of-00191.safetensors", "model.layers.121.self_attn.v_proj.weight": "model-00043-of-00191.safetensors", "model.layers.122.input_layernorm.weight": "model-00043-of-00191.safetensors", "model.layers.122.mlp.down_proj.weight": "model-00043-of-00191.safetensors", "model.layers.122.mlp.gate_proj.weight": "model-00044-of-00191.safetensors", "model.layers.122.mlp.up_proj.weight": "model-00044-of-00191.safetensors", "model.layers.122.post_attention_layernorm.weight": "model-00044-of-00191.safetensors", "model.layers.122.self_attn.k_proj.weight": "model-00044-of-00191.safetensors", "model.layers.122.self_attn.o_proj.weight": "model-00044-of-00191.safetensors", "model.layers.122.self_attn.q_proj.weight": "model-00044-of-00191.safetensors", "model.layers.122.self_attn.v_proj.weight": "model-00044-of-00191.safetensors", "model.layers.123.input_layernorm.weight": "model-00044-of-00191.safetensors", "model.layers.123.mlp.down_proj.weight": "model-00045-of-00191.safetensors", "model.layers.123.mlp.gate_proj.weight": "model-00045-of-00191.safetensors", "model.layers.123.mlp.up_proj.weight": "model-00046-of-00191.safetensors", "model.layers.123.post_attention_layernorm.weight": "model-00046-of-00191.safetensors", "model.layers.123.self_attn.k_proj.weight": "model-00046-of-00191.safetensors", "model.layers.123.self_attn.o_proj.weight": "model-00046-of-00191.safetensors", "model.layers.123.self_attn.q_proj.weight": "model-00046-of-00191.safetensors", "model.layers.123.self_attn.v_proj.weight": "model-00046-of-00191.safetensors", "model.layers.124.input_layernorm.weight": "model-00046-of-00191.safetensors", "model.layers.124.mlp.down_proj.weight": "model-00046-of-00191.safetensors", "model.layers.124.mlp.gate_proj.weight": "model-00047-of-00191.safetensors", "model.layers.124.mlp.up_proj.weight": "model-00047-of-00191.safetensors", "model.layers.124.post_attention_layernorm.weight": "model-00047-of-00191.safetensors", "model.layers.124.self_attn.k_proj.weight": "model-00047-of-00191.safetensors", "model.layers.124.self_attn.o_proj.weight": "model-00047-of-00191.safetensors", "model.layers.124.self_attn.q_proj.weight": "model-00047-of-00191.safetensors", "model.layers.124.self_attn.v_proj.weight": "model-00047-of-00191.safetensors", "model.layers.125.input_layernorm.weight": "model-00047-of-00191.safetensors", "model.layers.125.mlp.down_proj.weight": "model-00048-of-00191.safetensors", "model.layers.125.mlp.gate_proj.weight": "model-00048-of-00191.safetensors", "model.layers.125.mlp.up_proj.weight": "model-00049-of-00191.safetensors", "model.layers.125.post_attention_layernorm.weight": "model-00049-of-00191.safetensors", "model.layers.125.self_attn.k_proj.weight": "model-00049-of-00191.safetensors", "model.layers.125.self_attn.o_proj.weight": "model-00049-of-00191.safetensors", "model.layers.125.self_attn.q_proj.weight": "model-00049-of-00191.safetensors", "model.layers.125.self_attn.v_proj.weight": "model-00049-of-00191.safetensors", "model.layers.13.input_layernorm.weight": "model-00049-of-00191.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00049-of-00191.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00050-of-00191.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00050-of-00191.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00050-of-00191.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00050-of-00191.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00050-of-00191.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00050-of-00191.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00050-of-00191.safetensors", "model.layers.14.input_layernorm.weight": "model-00050-of-00191.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00051-of-00191.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00051-of-00191.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00052-of-00191.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00052-of-00191.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00052-of-00191.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00052-of-00191.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00052-of-00191.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00052-of-00191.safetensors", "model.layers.15.input_layernorm.weight": "model-00052-of-00191.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00052-of-00191.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00053-of-00191.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00053-of-00191.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00053-of-00191.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00053-of-00191.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00053-of-00191.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00053-of-00191.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00053-of-00191.safetensors", "model.layers.16.input_layernorm.weight": "model-00053-of-00191.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00054-of-00191.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00054-of-00191.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00055-of-00191.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00055-of-00191.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00055-of-00191.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00055-of-00191.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00055-of-00191.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00055-of-00191.safetensors", "model.layers.17.input_layernorm.weight": "model-00055-of-00191.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00055-of-00191.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00056-of-00191.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00056-of-00191.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00056-of-00191.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00056-of-00191.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00056-of-00191.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00056-of-00191.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00056-of-00191.safetensors", "model.layers.18.input_layernorm.weight": "model-00056-of-00191.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00057-of-00191.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00057-of-00191.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00058-of-00191.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00058-of-00191.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00058-of-00191.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00058-of-00191.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00058-of-00191.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00058-of-00191.safetensors", "model.layers.19.input_layernorm.weight": "model-00058-of-00191.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00058-of-00191.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00059-of-00191.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00059-of-00191.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00059-of-00191.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00059-of-00191.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00059-of-00191.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00059-of-00191.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00059-of-00191.safetensors", "model.layers.2.input_layernorm.weight": "model-00059-of-00191.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00060-of-00191.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00060-of-00191.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00061-of-00191.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00061-of-00191.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00061-of-00191.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00061-of-00191.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00061-of-00191.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00061-of-00191.safetensors", "model.layers.20.input_layernorm.weight": "model-00061-of-00191.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00061-of-00191.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00062-of-00191.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00062-of-00191.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00062-of-00191.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00062-of-00191.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00062-of-00191.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00062-of-00191.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00062-of-00191.safetensors", "model.layers.21.input_layernorm.weight": "model-00062-of-00191.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00063-of-00191.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00063-of-00191.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00064-of-00191.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00064-of-00191.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00064-of-00191.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00064-of-00191.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00064-of-00191.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00064-of-00191.safetensors", "model.layers.22.input_layernorm.weight": "model-00064-of-00191.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00064-of-00191.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00065-of-00191.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00065-of-00191.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00065-of-00191.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00065-of-00191.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00065-of-00191.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00065-of-00191.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00065-of-00191.safetensors", "model.layers.23.input_layernorm.weight": "model-00065-of-00191.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00066-of-00191.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00066-of-00191.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00067-of-00191.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00067-of-00191.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00067-of-00191.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00067-of-00191.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00067-of-00191.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00067-of-00191.safetensors", "model.layers.24.input_layernorm.weight": "model-00067-of-00191.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00067-of-00191.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00068-of-00191.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00068-of-00191.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00068-of-00191.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00068-of-00191.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00068-of-00191.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00068-of-00191.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00068-of-00191.safetensors", "model.layers.25.input_layernorm.weight": "model-00068-of-00191.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00069-of-00191.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00069-of-00191.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00070-of-00191.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00070-of-00191.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00070-of-00191.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00070-of-00191.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00070-of-00191.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00070-of-00191.safetensors", "model.layers.26.input_layernorm.weight": "model-00070-of-00191.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00070-of-00191.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00071-of-00191.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00071-of-00191.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00071-of-00191.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00071-of-00191.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00071-of-00191.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00071-of-00191.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00071-of-00191.safetensors", "model.layers.27.input_layernorm.weight": "model-00071-of-00191.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00072-of-00191.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00072-of-00191.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00073-of-00191.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00073-of-00191.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00073-of-00191.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00073-of-00191.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00073-of-00191.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00073-of-00191.safetensors", "model.layers.28.input_layernorm.weight": "model-00073-of-00191.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00073-of-00191.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00074-of-00191.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00074-of-00191.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00074-of-00191.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00074-of-00191.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00074-of-00191.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00074-of-00191.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00074-of-00191.safetensors", "model.layers.29.input_layernorm.weight": "model-00074-of-00191.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00075-of-00191.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00075-of-00191.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00076-of-00191.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00076-of-00191.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00076-of-00191.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00076-of-00191.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00076-of-00191.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00076-of-00191.safetensors", "model.layers.3.input_layernorm.weight": "model-00076-of-00191.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00076-of-00191.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00077-of-00191.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00077-of-00191.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00077-of-00191.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00077-of-00191.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00077-of-00191.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00077-of-00191.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00077-of-00191.safetensors", "model.layers.30.input_layernorm.weight": "model-00077-of-00191.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00078-of-00191.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00078-of-00191.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00079-of-00191.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00079-of-00191.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00079-of-00191.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00079-of-00191.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00079-of-00191.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00079-of-00191.safetensors", "model.layers.31.input_layernorm.weight": "model-00079-of-00191.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00079-of-00191.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00080-of-00191.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00080-of-00191.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00080-of-00191.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00080-of-00191.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00080-of-00191.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00080-of-00191.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00080-of-00191.safetensors", "model.layers.32.input_layernorm.weight": "model-00080-of-00191.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00081-of-00191.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00081-of-00191.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00082-of-00191.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00082-of-00191.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00082-of-00191.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00082-of-00191.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00082-of-00191.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00082-of-00191.safetensors", "model.layers.33.input_layernorm.weight": "model-00082-of-00191.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00082-of-00191.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00083-of-00191.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00083-of-00191.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00083-of-00191.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00083-of-00191.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00083-of-00191.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00083-of-00191.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00083-of-00191.safetensors", "model.layers.34.input_layernorm.weight": "model-00083-of-00191.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00084-of-00191.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00084-of-00191.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00085-of-00191.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00085-of-00191.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00085-of-00191.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00085-of-00191.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00085-of-00191.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00085-of-00191.safetensors", "model.layers.35.input_layernorm.weight": "model-00085-of-00191.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00085-of-00191.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00086-of-00191.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00086-of-00191.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00086-of-00191.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00086-of-00191.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00086-of-00191.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00086-of-00191.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00086-of-00191.safetensors", "model.layers.36.input_layernorm.weight": "model-00086-of-00191.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00087-of-00191.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00087-of-00191.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00088-of-00191.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00088-of-00191.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00088-of-00191.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00088-of-00191.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00088-of-00191.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00088-of-00191.safetensors", "model.layers.37.input_layernorm.weight": "model-00088-of-00191.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00088-of-00191.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00089-of-00191.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00089-of-00191.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00089-of-00191.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00089-of-00191.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00089-of-00191.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00089-of-00191.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00089-of-00191.safetensors", "model.layers.38.input_layernorm.weight": "model-00089-of-00191.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00090-of-00191.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00090-of-00191.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00091-of-00191.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00091-of-00191.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00091-of-00191.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00091-of-00191.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00091-of-00191.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00091-of-00191.safetensors", "model.layers.39.input_layernorm.weight": "model-00091-of-00191.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00091-of-00191.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00092-of-00191.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00092-of-00191.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00092-of-00191.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00092-of-00191.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00092-of-00191.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00092-of-00191.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00092-of-00191.safetensors", "model.layers.4.input_layernorm.weight": "model-00092-of-00191.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00093-of-00191.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00093-of-00191.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00094-of-00191.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00094-of-00191.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00094-of-00191.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00094-of-00191.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00094-of-00191.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00094-of-00191.safetensors", "model.layers.40.input_layernorm.weight": "model-00094-of-00191.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00094-of-00191.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00095-of-00191.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00095-of-00191.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00095-of-00191.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00095-of-00191.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00095-of-00191.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00095-of-00191.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00095-of-00191.safetensors", "model.layers.41.input_layernorm.weight": "model-00095-of-00191.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00096-of-00191.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00096-of-00191.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00097-of-00191.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00097-of-00191.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00097-of-00191.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00097-of-00191.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00097-of-00191.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00097-of-00191.safetensors", "model.layers.42.input_layernorm.weight": "model-00097-of-00191.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00097-of-00191.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00098-of-00191.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00098-of-00191.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00098-of-00191.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00098-of-00191.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00098-of-00191.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00098-of-00191.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00098-of-00191.safetensors", "model.layers.43.input_layernorm.weight": "model-00098-of-00191.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00099-of-00191.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00099-of-00191.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00100-of-00191.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00100-of-00191.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00100-of-00191.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00100-of-00191.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00100-of-00191.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00100-of-00191.safetensors", "model.layers.44.input_layernorm.weight": "model-00100-of-00191.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00100-of-00191.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00101-of-00191.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00101-of-00191.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00101-of-00191.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00101-of-00191.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00101-of-00191.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00101-of-00191.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00101-of-00191.safetensors", "model.layers.45.input_layernorm.weight": "model-00101-of-00191.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00102-of-00191.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00102-of-00191.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00103-of-00191.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00103-of-00191.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00103-of-00191.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00103-of-00191.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00103-of-00191.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00103-of-00191.safetensors", "model.layers.46.input_layernorm.weight": "model-00103-of-00191.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00103-of-00191.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00104-of-00191.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00104-of-00191.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00104-of-00191.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00104-of-00191.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00104-of-00191.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00104-of-00191.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00104-of-00191.safetensors", "model.layers.47.input_layernorm.weight": "model-00104-of-00191.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00105-of-00191.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00105-of-00191.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00106-of-00191.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00106-of-00191.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00106-of-00191.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00106-of-00191.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00106-of-00191.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00106-of-00191.safetensors", "model.layers.48.input_layernorm.weight": "model-00106-of-00191.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00106-of-00191.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00107-of-00191.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00107-of-00191.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00107-of-00191.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00107-of-00191.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00107-of-00191.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00107-of-00191.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00107-of-00191.safetensors", "model.layers.49.input_layernorm.weight": "model-00107-of-00191.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00108-of-00191.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00108-of-00191.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00109-of-00191.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00109-of-00191.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00109-of-00191.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00109-of-00191.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00109-of-00191.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00109-of-00191.safetensors", "model.layers.5.input_layernorm.weight": "model-00109-of-00191.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00109-of-00191.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00110-of-00191.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00110-of-00191.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00110-of-00191.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00110-of-00191.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00110-of-00191.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00110-of-00191.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00110-of-00191.safetensors", "model.layers.50.input_layernorm.weight": "model-00110-of-00191.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00111-of-00191.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00111-of-00191.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00112-of-00191.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00112-of-00191.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00112-of-00191.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00112-of-00191.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00112-of-00191.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00112-of-00191.safetensors", "model.layers.51.input_layernorm.weight": "model-00112-of-00191.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00112-of-00191.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00113-of-00191.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00113-of-00191.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00113-of-00191.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00113-of-00191.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00113-of-00191.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00113-of-00191.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00113-of-00191.safetensors", "model.layers.52.input_layernorm.weight": "model-00113-of-00191.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00114-of-00191.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00114-of-00191.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00115-of-00191.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00115-of-00191.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00115-of-00191.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00115-of-00191.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00115-of-00191.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00115-of-00191.safetensors", "model.layers.53.input_layernorm.weight": "model-00115-of-00191.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00115-of-00191.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00116-of-00191.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00116-of-00191.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00116-of-00191.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00116-of-00191.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00116-of-00191.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00116-of-00191.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00116-of-00191.safetensors", "model.layers.54.input_layernorm.weight": "model-00116-of-00191.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00117-of-00191.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00117-of-00191.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00118-of-00191.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00118-of-00191.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00118-of-00191.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00118-of-00191.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00118-of-00191.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00118-of-00191.safetensors", "model.layers.55.input_layernorm.weight": "model-00118-of-00191.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00118-of-00191.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00119-of-00191.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00119-of-00191.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00119-of-00191.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00119-of-00191.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00119-of-00191.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00119-of-00191.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00119-of-00191.safetensors", "model.layers.56.input_layernorm.weight": "model-00119-of-00191.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00120-of-00191.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00120-of-00191.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00121-of-00191.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00121-of-00191.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00121-of-00191.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00121-of-00191.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00121-of-00191.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00121-of-00191.safetensors", "model.layers.57.input_layernorm.weight": "model-00121-of-00191.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00121-of-00191.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00122-of-00191.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00122-of-00191.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00122-of-00191.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00122-of-00191.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00122-of-00191.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00122-of-00191.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00122-of-00191.safetensors", "model.layers.58.input_layernorm.weight": "model-00122-of-00191.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00123-of-00191.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00123-of-00191.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00124-of-00191.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00124-of-00191.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00124-of-00191.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00124-of-00191.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00124-of-00191.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00124-of-00191.safetensors", "model.layers.59.input_layernorm.weight": "model-00124-of-00191.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00124-of-00191.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00125-of-00191.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00125-of-00191.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00125-of-00191.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00125-of-00191.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00125-of-00191.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00125-of-00191.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00125-of-00191.safetensors", "model.layers.6.input_layernorm.weight": "model-00125-of-00191.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00126-of-00191.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00126-of-00191.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00127-of-00191.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00127-of-00191.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00127-of-00191.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00127-of-00191.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00127-of-00191.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00127-of-00191.safetensors", "model.layers.60.input_layernorm.weight": "model-00127-of-00191.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00127-of-00191.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00128-of-00191.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00128-of-00191.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00128-of-00191.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00128-of-00191.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00128-of-00191.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00128-of-00191.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00128-of-00191.safetensors", "model.layers.61.input_layernorm.weight": "model-00128-of-00191.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00129-of-00191.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00129-of-00191.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00130-of-00191.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00130-of-00191.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00130-of-00191.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00130-of-00191.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00130-of-00191.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00130-of-00191.safetensors", "model.layers.62.input_layernorm.weight": "model-00130-of-00191.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00130-of-00191.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00131-of-00191.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00131-of-00191.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00131-of-00191.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00131-of-00191.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00131-of-00191.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00131-of-00191.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00131-of-00191.safetensors", "model.layers.63.input_layernorm.weight": "model-00131-of-00191.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00132-of-00191.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00132-of-00191.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00133-of-00191.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00133-of-00191.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00133-of-00191.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00133-of-00191.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00133-of-00191.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00133-of-00191.safetensors", "model.layers.64.input_layernorm.weight": "model-00133-of-00191.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00133-of-00191.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00134-of-00191.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00134-of-00191.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00134-of-00191.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00134-of-00191.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00134-of-00191.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00134-of-00191.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00134-of-00191.safetensors", "model.layers.65.input_layernorm.weight": "model-00134-of-00191.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00135-of-00191.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00135-of-00191.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00136-of-00191.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00136-of-00191.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00136-of-00191.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00136-of-00191.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00136-of-00191.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00136-of-00191.safetensors", "model.layers.66.input_layernorm.weight": "model-00136-of-00191.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00136-of-00191.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00137-of-00191.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00137-of-00191.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00137-of-00191.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00137-of-00191.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00137-of-00191.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00137-of-00191.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00137-of-00191.safetensors", "model.layers.67.input_layernorm.weight": "model-00137-of-00191.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00138-of-00191.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00138-of-00191.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00139-of-00191.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00139-of-00191.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00139-of-00191.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00139-of-00191.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00139-of-00191.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00139-of-00191.safetensors", "model.layers.68.input_layernorm.weight": "model-00139-of-00191.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00139-of-00191.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00140-of-00191.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00140-of-00191.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00140-of-00191.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00140-of-00191.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00140-of-00191.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00140-of-00191.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00140-of-00191.safetensors", "model.layers.69.input_layernorm.weight": "model-00140-of-00191.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00141-of-00191.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00141-of-00191.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00142-of-00191.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00142-of-00191.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00142-of-00191.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00142-of-00191.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00142-of-00191.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00142-of-00191.safetensors", "model.layers.7.input_layernorm.weight": "model-00142-of-00191.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00142-of-00191.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00143-of-00191.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00143-of-00191.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00143-of-00191.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00143-of-00191.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00143-of-00191.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00143-of-00191.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00143-of-00191.safetensors", "model.layers.70.input_layernorm.weight": "model-00143-of-00191.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00144-of-00191.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00144-of-00191.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00145-of-00191.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00145-of-00191.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00145-of-00191.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00145-of-00191.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00145-of-00191.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00145-of-00191.safetensors", "model.layers.71.input_layernorm.weight": "model-00145-of-00191.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00145-of-00191.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00146-of-00191.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00146-of-00191.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00146-of-00191.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00146-of-00191.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00146-of-00191.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00146-of-00191.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00146-of-00191.safetensors", "model.layers.72.input_layernorm.weight": "model-00146-of-00191.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00147-of-00191.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00147-of-00191.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00148-of-00191.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00148-of-00191.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00148-of-00191.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00148-of-00191.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00148-of-00191.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00148-of-00191.safetensors", "model.layers.73.input_layernorm.weight": "model-00148-of-00191.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00148-of-00191.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00149-of-00191.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00149-of-00191.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00149-of-00191.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00149-of-00191.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00149-of-00191.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00149-of-00191.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00149-of-00191.safetensors", "model.layers.74.input_layernorm.weight": "model-00149-of-00191.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00150-of-00191.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00150-of-00191.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00151-of-00191.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00151-of-00191.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00151-of-00191.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00151-of-00191.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00151-of-00191.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00151-of-00191.safetensors", "model.layers.75.input_layernorm.weight": "model-00151-of-00191.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00151-of-00191.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00152-of-00191.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00152-of-00191.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00152-of-00191.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00152-of-00191.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00152-of-00191.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00152-of-00191.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00152-of-00191.safetensors", "model.layers.76.input_layernorm.weight": "model-00152-of-00191.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00153-of-00191.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00153-of-00191.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00154-of-00191.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00154-of-00191.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00154-of-00191.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00154-of-00191.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00154-of-00191.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00154-of-00191.safetensors", "model.layers.77.input_layernorm.weight": "model-00154-of-00191.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00154-of-00191.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00155-of-00191.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00155-of-00191.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00155-of-00191.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00155-of-00191.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00155-of-00191.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00155-of-00191.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00155-of-00191.safetensors", "model.layers.78.input_layernorm.weight": "model-00155-of-00191.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00156-of-00191.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00156-of-00191.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00157-of-00191.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00157-of-00191.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00157-of-00191.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00157-of-00191.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00157-of-00191.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00157-of-00191.safetensors", "model.layers.79.input_layernorm.weight": "model-00157-of-00191.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00157-of-00191.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00158-of-00191.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00158-of-00191.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00158-of-00191.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00158-of-00191.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00158-of-00191.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00158-of-00191.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00158-of-00191.safetensors", "model.layers.8.input_layernorm.weight": "model-00158-of-00191.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00159-of-00191.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00159-of-00191.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00160-of-00191.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00160-of-00191.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00160-of-00191.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00160-of-00191.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00160-of-00191.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00160-of-00191.safetensors", "model.layers.80.input_layernorm.weight": "model-00160-of-00191.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00160-of-00191.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00161-of-00191.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00161-of-00191.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00161-of-00191.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00161-of-00191.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00161-of-00191.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00161-of-00191.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00161-of-00191.safetensors", "model.layers.81.input_layernorm.weight": "model-00161-of-00191.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00162-of-00191.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00162-of-00191.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00163-of-00191.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00163-of-00191.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00163-of-00191.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00163-of-00191.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00163-of-00191.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00163-of-00191.safetensors", "model.layers.82.input_layernorm.weight": "model-00163-of-00191.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00163-of-00191.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00164-of-00191.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00164-of-00191.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00164-of-00191.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00164-of-00191.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00164-of-00191.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00164-of-00191.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00164-of-00191.safetensors", "model.layers.83.input_layernorm.weight": "model-00164-of-00191.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00165-of-00191.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00165-of-00191.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00166-of-00191.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00166-of-00191.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00166-of-00191.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00166-of-00191.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00166-of-00191.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00166-of-00191.safetensors", "model.layers.84.input_layernorm.weight": "model-00166-of-00191.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00166-of-00191.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00167-of-00191.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00167-of-00191.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00167-of-00191.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00167-of-00191.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00167-of-00191.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00167-of-00191.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00167-of-00191.safetensors", "model.layers.85.input_layernorm.weight": "model-00167-of-00191.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00168-of-00191.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00168-of-00191.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00169-of-00191.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00169-of-00191.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00169-of-00191.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00169-of-00191.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00169-of-00191.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00169-of-00191.safetensors", "model.layers.86.input_layernorm.weight": "model-00169-of-00191.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00169-of-00191.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00170-of-00191.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00170-of-00191.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00170-of-00191.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00170-of-00191.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00170-of-00191.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00170-of-00191.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00170-of-00191.safetensors", "model.layers.87.input_layernorm.weight": "model-00170-of-00191.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00171-of-00191.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00171-of-00191.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00172-of-00191.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00172-of-00191.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00172-of-00191.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00172-of-00191.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00172-of-00191.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00172-of-00191.safetensors", "model.layers.88.input_layernorm.weight": "model-00172-of-00191.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00172-of-00191.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00173-of-00191.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00173-of-00191.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00173-of-00191.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00173-of-00191.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00173-of-00191.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00173-of-00191.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00173-of-00191.safetensors", "model.layers.89.input_layernorm.weight": "model-00173-of-00191.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00174-of-00191.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00174-of-00191.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00175-of-00191.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00175-of-00191.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00175-of-00191.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00175-of-00191.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00175-of-00191.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00175-of-00191.safetensors", "model.layers.9.input_layernorm.weight": "model-00175-of-00191.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00175-of-00191.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00176-of-00191.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00176-of-00191.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00176-of-00191.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00176-of-00191.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00176-of-00191.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00176-of-00191.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00176-of-00191.safetensors", "model.layers.90.input_layernorm.weight": "model-00176-of-00191.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00177-of-00191.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00177-of-00191.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00178-of-00191.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00178-of-00191.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00178-of-00191.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00178-of-00191.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00178-of-00191.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00178-of-00191.safetensors", "model.layers.91.input_layernorm.weight": "model-00178-of-00191.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00178-of-00191.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00179-of-00191.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00179-of-00191.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00179-of-00191.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00179-of-00191.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00179-of-00191.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00179-of-00191.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00179-of-00191.safetensors", "model.layers.92.input_layernorm.weight": "model-00179-of-00191.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00180-of-00191.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00180-of-00191.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00181-of-00191.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00181-of-00191.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00181-of-00191.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00181-of-00191.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00181-of-00191.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00181-of-00191.safetensors", "model.layers.93.input_layernorm.weight": "model-00181-of-00191.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00181-of-00191.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00182-of-00191.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00182-of-00191.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00182-of-00191.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00182-of-00191.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00182-of-00191.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00182-of-00191.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00182-of-00191.safetensors", "model.layers.94.input_layernorm.weight": "model-00182-of-00191.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00183-of-00191.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00183-of-00191.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00184-of-00191.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00184-of-00191.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00184-of-00191.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00184-of-00191.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00184-of-00191.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00184-of-00191.safetensors", "model.layers.95.input_layernorm.weight": "model-00184-of-00191.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00184-of-00191.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00185-of-00191.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00185-of-00191.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00185-of-00191.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00185-of-00191.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00185-of-00191.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00185-of-00191.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00185-of-00191.safetensors", "model.layers.96.input_layernorm.weight": "model-00185-of-00191.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00186-of-00191.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00186-of-00191.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00187-of-00191.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00187-of-00191.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00187-of-00191.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00187-of-00191.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00187-of-00191.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00187-of-00191.safetensors", "model.layers.97.input_layernorm.weight": "model-00187-of-00191.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00187-of-00191.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00188-of-00191.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00188-of-00191.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00188-of-00191.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00188-of-00191.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00188-of-00191.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00188-of-00191.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00188-of-00191.safetensors", "model.layers.98.input_layernorm.weight": "model-00188-of-00191.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00189-of-00191.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00189-of-00191.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00190-of-00191.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00190-of-00191.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00190-of-00191.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00190-of-00191.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00190-of-00191.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00190-of-00191.safetensors", "model.layers.99.input_layernorm.weight": "model-00190-of-00191.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00190-of-00191.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00191-of-00191.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00191-of-00191.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00191-of-00191.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00191-of-00191.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00191-of-00191.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00191-of-00191.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00191-of-00191.safetensors", "model.norm.weight": "model-00191-of-00191.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c68051fe3c4d23234a59316bc52d21f6e3a4182c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}