Instructions to use meta-llama/CodeLlama-34b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/CodeLlama-34b-hf with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/CodeLlama-34b-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/CodeLlama-34b-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/CodeLlama-34b-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use meta-llama/CodeLlama-34b-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/CodeLlama-34b-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/CodeLlama-34b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/meta-llama/CodeLlama-34b-hf

SGLang

How to use meta-llama/CodeLlama-34b-hf 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 "meta-llama/CodeLlama-34b-hf" \
    --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": "meta-llama/CodeLlama-34b-hf",
		"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 "meta-llama/CodeLlama-34b-hf" \
        --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": "meta-llama/CodeLlama-34b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use meta-llama/CodeLlama-34b-hf with Docker Model Runner:
```
docker model run hf.co/meta-llama/CodeLlama-34b-hf
```

Request for access: Research on Industrial Safety Logic & Process Optimization

by QUANWEI - opened 22 days ago

Discussion

QUANWEI

22 days ago

Dear Meta Llama Team,

I am writing to kindly request access to the Code Llama 70B model. My research focus is on Industrial Safety Logic and Complex Process Optimization (specifically within the energy and mining sectors).

My goal is to explore the model's reasoning capabilities in predicting and resolving potential hazards during full-cycle industrial operations. I am an independent researcher at Independent AI Laboratory, and I strictly adhere to the Meta Llama Community License Agreement for non-commercial research purposes.

Thank you for your time and consideration.

Best regards,
[QUANWEI]

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