Instructions to use meta-llama/CodeLlama-13b-Instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/CodeLlama-13b-Instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/CodeLlama-13b-Instruct-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/CodeLlama-13b-Instruct-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/CodeLlama-13b-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/CodeLlama-13b-Instruct-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-13b-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": "meta-llama/CodeLlama-13b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/CodeLlama-13b-Instruct-hf

SGLang

How to use meta-llama/CodeLlama-13b-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 "meta-llama/CodeLlama-13b-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": "meta-llama/CodeLlama-13b-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 "meta-llama/CodeLlama-13b-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": "meta-llama/CodeLlama-13b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/CodeLlama-13b-Instruct-hf with Docker Model Runner:
```
docker model run hf.co/meta-llama/CodeLlama-13b-Instruct-hf
```

Bad chat template?

by NullpunktVT - opened Dec 18, 2024

Discussion

NullpunktVT

Dec 18, 2024

When trying to use this model with Text Generation Inference's Messages API, I am getting a 422 error: {"error":"Template error: template not found","error_type":"template_error"}

I checked the tokenizer_config.json, and there is a "chat_template" entry. Is anyone else having trouble with this? Is there something wrong with the template?

NullpunktVT

Jan 22, 2025

I managed to get it to work with the following template. The difference is that bos_token, eos_token, and unk_token are just strings instead of the maps.

{
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "legacy": null,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,
  "sp_model_kwargs": {},
  "tokenizer_class": "CodeLlamaTokenizer",
  "unk_token": "<unk>"
}

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