codellama
/

CodeLlama-34b-Instruct-hf

Text Generation

text-generation-inference

Model card Files Files and versions

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

Libraries

How to use codellama/CodeLlama-34b-Instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="codellama/CodeLlama-34b-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-34b-Instruct-hf")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-34b-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

How to use codellama/CodeLlama-34b-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-34b-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-34b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codellama/CodeLlama-34b-Instruct-hf

How to use codellama/CodeLlama-34b-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-34b-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-34b-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-34b-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-34b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Resources

View closed (11)

Model not loaded on the server

#28 opened almost 2 years ago by

Best codeLlama model for query SQL generation

#24 opened over 2 years ago by

HuggingChat in Python

#23 opened over 2 years ago by

Adding Evaluation Results

#22 opened over 2 years ago by

leaderboard-pr-bot

429 Response Status on subsequent Inference API requests.

#21 opened over 2 years ago by

[AUTOMATED] Model Memory Requirements

#20 opened over 2 years ago by

model-sizer-bot

Does the pretraining dataset and finetuning dataset include Rust programming language?

#19 opened over 2 years ago by

Locally deployed models have poor performance. model:CodeLlama-34b-Instruct-hf

#18 opened over 2 years ago by

KeyError: "filename 'storages' not found"

#17 opened over 2 years ago by

Inference API doesn't seem to support 100k context window

#16 opened over 2 years ago by

The difference between the playground and the offline model

#15 opened over 2 years ago by

Update tokenizer_config.json

#14 opened over 2 years ago by

[AUTOMATED] Model Memory Requirements

#13 opened over 2 years ago by

model-sizer-bot

Mismatch b/w tokenizer and model embedding. What to use?

#12 opened over 2 years ago by

What is right GPU to run this

#7 opened over 2 years ago by

Model pads response with newlines up to max_length

#6 opened over 2 years ago by

Keep normal style for title?

#1 opened over 2 years ago by