Instructions to use facebook/layerskip-llama3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use facebook/layerskip-llama3-8B with Transformers:

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

pipe = pipeline("text-generation", model="facebook/layerskip-llama3-8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("facebook/layerskip-llama3-8B")
model = AutoModelForCausalLM.from_pretrained("facebook/layerskip-llama3-8B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use facebook/layerskip-llama3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "facebook/layerskip-llama3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "facebook/layerskip-llama3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/facebook/layerskip-llama3-8B

SGLang

How to use facebook/layerskip-llama3-8B 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 "facebook/layerskip-llama3-8B" \
    --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": "facebook/layerskip-llama3-8B",
		"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 "facebook/layerskip-llama3-8B" \
        --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": "facebook/layerskip-llama3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use facebook/layerskip-llama3-8B with Docker Model Runner:
```
docker model run hf.co/facebook/layerskip-llama3-8B
```

Request rejected: Could you please reset my application status?

by deleted - opened Mar 12

Discussion

deleted

Mar 12

Hello, I am writing to politely request a reset of my access application status for this model. My previous request was rejected, which I believe was due to submitting incomplete information about my specific use case.
I would like to clarify that my request is strictly for non-commercial academic research. I am a second-year graduate student at Beijing Information Science and Technology University (BISTU).
My current research focuses on the inference mechanisms of Large Language Models, specifically investigating "early exit" strategies. I am analyzing and comparing the prediction results at various intermediate layers (early exits) against the final prediction of the full model. Access to this model is essential for conducting my experiments and evaluating decoding efficiency.
Could you please kindly reset my application status so that I can submit a complete and detailed request with this information?
Thank you for your time and understanding.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment