Instructions to use TheBloke/WizardCoder-15B-1.0-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/WizardCoder-15B-1.0-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/WizardCoder-15B-1.0-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/WizardCoder-15B-1.0-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/WizardCoder-15B-1.0-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/WizardCoder-15B-1.0-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/WizardCoder-15B-1.0-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-15B-1.0-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/WizardCoder-15B-1.0-GPTQ

SGLang

How to use TheBloke/WizardCoder-15B-1.0-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-15B-1.0-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-15B-1.0-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-15B-1.0-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-15B-1.0-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/WizardCoder-15B-1.0-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/WizardCoder-15B-1.0-GPTQ
```

question about tokens limit

by sunzx0810 - opened Jun 26, 2023

Discussion

sunzx0810

Jun 26, 2023

when testing the model in a local environment by directly running the code, I input a 567 tokens' question and raise error 'list index out of range' which seems to tell me that the output exceeds in 2000 tokens. However, the question works well both on demo and text generation webui. why webui can generate answers word by word? And I also find that the response from the local model will try to edit the instructions but the webui and demo will not. It's very confusing.

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