Instructions to use TheBloke/WizardCoder-Python-34B-V1.0-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/WizardCoder-Python-34B-V1.0-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/WizardCoder-Python-34B-V1.0-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/WizardCoder-Python-34B-V1.0-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/WizardCoder-Python-34B-V1.0-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/WizardCoder-Python-34B-V1.0-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/WizardCoder-Python-34B-V1.0-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/WizardCoder-Python-34B-V1.0-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/WizardCoder-Python-34B-V1.0-GPTQ

SGLang

How to use TheBloke/WizardCoder-Python-34B-V1.0-GPTQ 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/WizardCoder-Python-34B-V1.0-GPTQ" \
    --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/WizardCoder-Python-34B-V1.0-GPTQ",
		"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/WizardCoder-Python-34B-V1.0-GPTQ" \
        --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/WizardCoder-Python-34B-V1.0-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/WizardCoder-Python-34B-V1.0-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/WizardCoder-Python-34B-V1.0-GPTQ
```

Does the result right?

by lucasjin - opened Aug 27, 2023

Discussion

lucasjin

Aug 27, 2023

The other (coderllama GPTQ) model seems corrupted, the result not right.

Does this GPTQ weights is right?

kajuberdut

Aug 27, 2023

•

edited Aug 27, 2023

I haven't tried this one but I have used TheBloke_CodeLlama-34B-Python-GPTQ_gptq-4bit-32g-actorder_True for several things and that model works fine.

WizardCoder-Python (this model) is an instruct tuned model while CodeLlama-34B-Python is a continuation model so there is no prompt template and you must write enough of whatever code you want that the model can see what it should finish. If you were running into trouble with the fact that CodeLlama-Python doesn't let you ask questions / give instructions in a template, WizardCoder might be a better choice for you!

lucasjin

Aug 28, 2023

thanks, but I preivous tried also a instructed model.

What diffference between this one and TheBloke_CodeLlama-34B-Python-GPTQ_gptq-4bit-32g-actorder_True ?

kajuberdut

Aug 28, 2023

•

edited Aug 28, 2023

thanks, but I preivous tried also a instructed model.

What diffference between this one and TheBloke_CodeLlama-34B-Python-GPTQ_gptq-4bit-32g-actorder_True ?

I don't know about this wizard coder model but if you are looking for verified good performance check out the screenshots here using the Phind model: https://huggingface.co/TheBloke/Phind-CodeLlama-34B-Python-v1-GGUF/discussions/1#64ead499e74f54587cd6336d

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