Instructions to use codellama/CodeLlama-7b-Instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codellama/CodeLlama-7b-Instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="codellama/CodeLlama-7b-Instruct-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-7b-Instruct-hf")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-Instruct-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codellama/CodeLlama-7b-Instruct-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codellama/CodeLlama-7b-Instruct-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-7b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codellama/CodeLlama-7b-Instruct-hf

SGLang

How to use codellama/CodeLlama-7b-Instruct-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-7b-Instruct-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-7b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-7b-Instruct-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-7b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codellama/CodeLlama-7b-Instruct-hf with Docker Model Runner:
```
docker model run hf.co/codellama/CodeLlama-7b-Instruct-hf
```

Can't reproduce the results on Humaneval

#18

by JingyaoLi - opened Oct 11, 2023

Discussion

JingyaoLi

Oct 11, 2023

Hello, may I ask how you conducted testing on Humaneval? I attempted to test using the two methods you provided in your Hugging Face blog, including code completion and code infilling on Humaneval. However, I only achieved results of 22% and 25% on Instruct CodeLLama 7B, which is far from the reported 35%.

args.max_length = 1024

if args.task == 'code-infilling':
    tokenizer = transformers.AutoTokenizer.from_pretrained(args.model_path)
    pipeline = transformers.pipeline(
        "text-generation",
        model=args.model_path,
        torch_dtype=torch.float16,
        device_map="auto",
    )
    for task_id in problems:
        prompt = problems[task_id]['question'] + '<FILL_ME>\n    return result'
        input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to("cuda")
        output = model.generate(input_ids, max_new_tokens=args.max_length,)
        output = output[0].to("cpu")
        filling = tokenizer.decode(output[input_ids.shape[1]:], skip_special_tokens=True)
        completion = prompt.replace("<FILL_ME>", filling)

elif args.task == 'code-completion':
    tokenizer = transformers.AutoTokenizer.from_pretrained(args.model_path)
    model = transformers.AutoModelForCausalLM.from_pretrained(
        args.model_path,
        torch_dtype=torch.float16
    ).to("cuda")
    for task_id in problems:
        completion = pipeline(
            prompt,
            do_sample=True,
            temperature=0.2,
            top_p=0.9,
            num_return_sequences=1,
            eos_token_id=tokenizer.eos_token_id,
            max_length=args.max_length,
        )[0]['generated_text'].strip()

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