Instructions to use onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM")
model = AutoModelForCausalLM.from_pretrained("onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM

SGLang

How to use onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM 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 "onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM with Docker Model Runner:
```
docker model run hf.co/onnx-internal-testing/tiny-random-ModernBertDecoderForCausalLM
```

tiny-random-ModernBertDecoderForCausalLM / config.json

Xenova HF Staff

Match "layer_types" length with "num_hidden_layers" (#1)

0668913 about 2 months ago

raw

history blame contribute delete

1.45 kB

	{
	"architectures": [
	"ModernBertDecoderForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token": "[CLS]",
	"bos_token_id": 50281,
	"causal_mask": true,
	"classifier_activation": "gelu",
	"classifier_bias": false,
	"classifier_dropout": 0.0,
	"classifier_pooling": "mean",
	"cls_token_id": 50281,
	"decoder_bias": true,
	"deterministic_flash_attn": false,
	"embedding_dropout": 0.0,
	"eos_token": "[SEP]",
	"eos_token_id": 50282,
	"global_attn_every_n_layers": 3,
	"global_rope_theta": 160000.0,
	"gradient_checkpointing": false,
	"hidden_activation": "gelu",
	"hidden_size": 32,
	"initializer_cutoff_factor": 2.0,
	"initializer_range": 0.02,
	"intermediate_size": 32,
	"is_causal": true,
	"layer_norm_eps": 1e-05,
	"layer_types": [
	"full_attention",
	"sliding_attention"
	],
	"local_rope_theta": 160000.0,
	"masked_prediction": false,
	"max_position_embeddings": 7999,
	"mlp_bias": false,
	"mlp_dropout": 0.0,
	"model_type": "modernbert-decoder",
	"norm_bias": false,
	"norm_eps": 1e-05,
	"num_attention_heads": 4,
	"num_hidden_layers": 2,
	"pad_token_id": 50283,
	"position_embedding_type": "sans_pos",
	"reference_compile": false,
	"sep_token_id": 50282,
	"sliding_window": 64,
	"tokenizer_class": "PreTrainedTokenizerFast",
	"torch_dtype": "float32",
	"transformers_version": "4.54.0.dev0",
	"unk_token": "[UNK]",
	"use_cache": true,
	"vocab_size": 50368
	}