Instructions to use codellama/CodeLlama-70b-Python-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codellama/CodeLlama-70b-Python-hf with Transformers:

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

pipe = pipeline("text-generation", model="codellama/CodeLlama-70b-Python-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-70b-Python-hf")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-70b-Python-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codellama/CodeLlama-70b-Python-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codellama/CodeLlama-70b-Python-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-70b-Python-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codellama/CodeLlama-70b-Python-hf

SGLang

How to use codellama/CodeLlama-70b-Python-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 "codellama/CodeLlama-70b-Python-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": "codellama/CodeLlama-70b-Python-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 "codellama/CodeLlama-70b-Python-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": "codellama/CodeLlama-70b-Python-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codellama/CodeLlama-70b-Python-hf with Docker Model Runner:
```
docker model run hf.co/codellama/CodeLlama-70b-Python-hf
```

Example code

by HFMSalazar - opened Jan 31, 2024

Discussion

HFMSalazar

Jan 31, 2024

Could we have a working example using this model? Always nice to have a place to start that is not a rabbit hole.

enochlev

Jan 31, 2024

Here is an example... but I would refer to a much smaller model 7B or 13B. You need atleast 48 gb gpu for this one, and that if you quantize it.

from transformers import pipeline
import torch

# Check if CUDA (GPU support) is available and use it; otherwise, use CPU
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the pipeline with your specified model
pipe = pipeline("text-generation", model="codellama/CodeLlama-70b-Python-hf", device=device)

# Enable 16-bit precision (fp16)
if device == "cuda":
    pipe.model.half()

# Example usage of the pipeline
text = pipe("Example input text", max_length=50)[0]['generated_text']
print(text)

ArthurZ

Code Llama org Feb 2, 2024

Feel free to open a PR to add this to the readme for example!

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