Instructions to use DanielHesslow/Mistral_First2Layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DanielHesslow/Mistral_First2Layers with Transformers:

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

pipe = pipeline("text-generation", model="DanielHesslow/Mistral_First2Layers")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DanielHesslow/Mistral_First2Layers")
model = AutoModelForCausalLM.from_pretrained("DanielHesslow/Mistral_First2Layers")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DanielHesslow/Mistral_First2Layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DanielHesslow/Mistral_First2Layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DanielHesslow/Mistral_First2Layers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DanielHesslow/Mistral_First2Layers

SGLang

How to use DanielHesslow/Mistral_First2Layers 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 "DanielHesslow/Mistral_First2Layers" \
    --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": "DanielHesslow/Mistral_First2Layers",
		"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 "DanielHesslow/Mistral_First2Layers" \
        --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": "DanielHesslow/Mistral_First2Layers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DanielHesslow/Mistral_First2Layers with Docker Model Runner:
```
docker model run hf.co/DanielHesslow/Mistral_First2Layers
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Mistral 7b model, but cut down to use only the first two layers.

For debugging

Downloads last month: 8

Safetensors

Model size

0.7B params

Tensor type

F32