Instructions to use schonsense/70B_flu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schonsense/70B_flu with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="schonsense/70B_flu")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schonsense/70B_flu")
model = AutoModelForCausalLM.from_pretrained("schonsense/70B_flu")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use schonsense/70B_flu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schonsense/70B_flu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schonsense/70B_flu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schonsense/70B_flu

SGLang

How to use schonsense/70B_flu with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "schonsense/70B_flu" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schonsense/70B_flu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "schonsense/70B_flu" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schonsense/70B_flu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schonsense/70B_flu with Docker Model Runner:
```
docker model run hf.co/schonsense/70B_flu
```

flu

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SCE merge method using D:\mergekit\yamls\IPOplectic as a base.

Models Merged

The following models were included in the merge:

schonsense/70B_lampblack_writers_room
LatitudeGames/Nova-70B-Llama-3.3
LatitudeGames/Wayfarer-Large-70B-Llama-3.3
D:\mergekit\yamls\sce_smoot_v2

Configuration

The following YAML configuration was used to produce this model:

merge_method: sce
select_topk: 0.25

models:


  - model: "D:\\mergekit\\yamls\\IPOplectic"
  - model: "D:\\mergekit\\yamls\\sce_smoot_v2"
  - model: schonsense/70B_lampblack_writers_room
  - model: LatitudeGames/Nova-70B-Llama-3.3
  - model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3


base_model: "D:\\mergekit\\yamls\\IPOplectic"

parameters:
  normalize: false
  int8_mask: true

dtype: float32
out_dtype: bfloat16

tokenizer:
  source: union
  pad_to_multiple_of: 8

Downloads last month: 6

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for schonsense/70B_flu

LatitudeGames/Nova-70B-Llama-3.3

LatitudeGames/Wayfarer-Large-70B-Llama-3.3

schonsense/70B_lampblack_writers_room

Merge model

this model

Paper for schonsense/70B_flu

FuseChat: Knowledge Fusion of Chat Models

Paper • 2408.07990 • Published Aug 15, 2024 • 15