Instructions to use TheBloke/CodeLlama-13B-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/CodeLlama-13B-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/CodeLlama-13B-fp16", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/CodeLlama-13B-fp16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-13B-fp16", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/CodeLlama-13B-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/CodeLlama-13B-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/CodeLlama-13B-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/CodeLlama-13B-fp16

SGLang

How to use TheBloke/CodeLlama-13B-fp16 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 "TheBloke/CodeLlama-13B-fp16" \
    --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": "TheBloke/CodeLlama-13B-fp16",
		"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 "TheBloke/CodeLlama-13B-fp16" \
        --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": "TheBloke/CodeLlama-13B-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/CodeLlama-13B-fp16 with Docker Model Runner:
```
docker model run hf.co/TheBloke/CodeLlama-13B-fp16
```

Update config.json

by jkeisling - opened Aug 24, 2023

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

jkeisling

Aug 24, 2023

•

edited Aug 24, 2023

The tokenizer vocab size for CodeLlama 13b, 7b got expanded w/ infill tokens (see research paper pg 4). I checked and the new vocab size is 32,016. Inference works fine w/ the incorrect count but PEFT training requires the vocab size to be right. Edited config locally manually and training works now

Update config.json01d95112

TheBloke

Owner Aug 24, 2023

Thanks yeah, I've already fixed it

TheBloke changed pull request status to closed Aug 24, 2023

TheBloke

Owner Aug 24, 2023

oh shit I hadn't done this one for some reason

TheBloke changed pull request status to open Aug 24, 2023

TheBloke changed pull request status to merged Aug 24, 2023

TheBloke

Owner Aug 24, 2023

Thanks!

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