Instructions to use facebook/llm-compiler-13b-ftd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use facebook/llm-compiler-13b-ftd with Transformers:

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

pipe = pipeline("text-generation", model="facebook/llm-compiler-13b-ftd")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("facebook/llm-compiler-13b-ftd")
model = AutoModelForCausalLM.from_pretrained("facebook/llm-compiler-13b-ftd")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use facebook/llm-compiler-13b-ftd with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "facebook/llm-compiler-13b-ftd"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "facebook/llm-compiler-13b-ftd",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/facebook/llm-compiler-13b-ftd

SGLang

How to use facebook/llm-compiler-13b-ftd 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/llm-compiler-13b-ftd" \
    --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/llm-compiler-13b-ftd",
		"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/llm-compiler-13b-ftd" \
        --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/llm-compiler-13b-ftd",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use facebook/llm-compiler-13b-ftd with Docker Model Runner:
```
docker model run hf.co/facebook/llm-compiler-13b-ftd
```

Request for Affiliation Code to Access Project Resources

by nsdesigner - opened Oct 19, 2024

Discussion

nsdesigner

Oct 19, 2024

Hi. I'm a big fan of compiler technologies and heard this project from the web.

I’m eager to dive deeper into how this breakthrough compiler works and explore potential opportunities to contribute and improve it.

However, I noticed that access to the project requires an affiliation code.

Could someone kindly guide me on how I can obtain this code or what steps I should follow to gain access?

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