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

Libraries

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

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

pipe = pipeline("text-generation", model="codellama/CodeLlama-7b-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-7b-hf")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codellama/CodeLlama-7b-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-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-7b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use codellama/CodeLlama-7b-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-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-7b-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-7b-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-7b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

CodeLlamaTokenizer

#11

by pcuenq HF Staff - opened Aug 28, 2023

base: refs/heads/main

←

from: refs/pr/11

Discussion Files changed

-1

pcuenq

Code Llama org Aug 28, 2023

No description provided.

CodeLlamaTokenizerae1b4417

osanseviero changed pull request status to merged Aug 28, 2023

cassanof

Aug 28, 2023

•

edited Aug 28, 2023

I'm having issues with this, AutoTokenizer doesn't seem to be able to import it:

Traceback (most recent call last):
  File "/home/federico/MultiPL-E/automodel.py", line 92, in <module>
    main()
  File "/home/federico/MultiPL-E/automodel.py", line 87, in main
    model = Model(args.name, args.revision, args.tokenizer_name, args.tokenizer_revision)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/federico/MultiPL-E/automodel.py", line 14, in __init__
    self.tokenizer = AutoTokenizer.from_pretrained(tokenizer_name or name, padding_side="left", trust_remote_code=True)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/federico/santacoder-finetuning-lua/.env/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 731, in from_pretrained
    raise ValueError(
ValueError: Tokenizer class CodeLlamaTokenizer does not exist or is not currently imported.

I updated the transformers library to the latest on git

pcuenq

Code Llama org Aug 28, 2023

hmmm, strange, it works with transformers @ main for me. Could you please paste the output from transformers-cli env and provide a short reproduction snippet?

cassanof

Aug 28, 2023

fixed! fyi, you have to uninstall tokenizers if you were on the @main before the addition of CodeLlamaTokenizer

pcuenq

Code Llama org Aug 29, 2023

Oh, I see! Glad you could solve it :)

ArthurZ

Code Llama org Sep 4, 2023

You should not have to uninstall tokenizers, it's completely unrelated as the class we used online is CodeLlamaTokenizer and not CodeLlamaTokenizerFast

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