Instructions to use TheBloke/CodeLlama-34B-Instruct-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/CodeLlama-34B-Instruct-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/CodeLlama-34B-Instruct-fp16", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/CodeLlama-34B-Instruct-fp16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-34B-Instruct-fp16", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/CodeLlama-34B-Instruct-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/CodeLlama-34B-Instruct-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-34B-Instruct-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/CodeLlama-34B-Instruct-fp16

SGLang

How to use TheBloke/CodeLlama-34B-Instruct-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-34B-Instruct-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-34B-Instruct-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-34B-Instruct-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-34B-Instruct-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/CodeLlama-34B-Instruct-fp16 with Docker Model Runner:
```
docker model run hf.co/TheBloke/CodeLlama-34B-Instruct-fp16
```

The fp16 model has the same size as the original model

by adnan-ahmad-tub - opened Aug 28, 2023

Discussion

adnan-ahmad-tub

Aug 28, 2023

CodeLlama-34B-Instruct-fp16 has 7*9GB checkpoints, same as
CodeLlama-34B-Instruct. Shouldn't the fp16 quantization reduce the model size?

TheBloke

Owner Aug 28, 2023

fp16 isn't a quantisation, it's the original model. You can use CodeLlama/CodeLlama-34B-Instruct-HF now. I put this repo up because originally there was no official source for these models on HF, but now there is.

adnan-ahmad-tub

Aug 28, 2023

Is it the same as loading the model using model = AutoModelForCausalLM.from_pretrained(model_directory, device_map = 'auto', torch_dtype=torch.float16)

s11005349

Nov 2, 2023

Hi
Does anyone have some GPU requirement / suggestions using this model?
I'm planing buying some A6000 or something to run this locally.
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