Instructions to use TheBloke/WizardCoder-Python-13B-V1.0-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/WizardCoder-Python-13B-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-13B-V1.0-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/WizardCoder-Python-13B-V1.0-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/WizardCoder-Python-13B-V1.0-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/WizardCoder-Python-13B-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-13B-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-13B-V1.0-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/WizardCoder-Python-13B-V1.0-GPTQ

SGLang

How to use TheBloke/WizardCoder-Python-13B-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-13B-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-13B-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-13B-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-13B-V1.0-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/WizardCoder-Python-13B-V1.0-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/WizardCoder-Python-13B-V1.0-GPTQ
```

ImportError: libcudart.so.12: cannot open shared object file: No such file or directory

by Rohith1016 - opened Nov 9, 2023

Discussion

Rohith1016

Nov 9, 2023

Getting Error while downloading the Model
ImportError: libcudart.so.12: cannot open shared object file: No such file or directory

ImportError Traceback (most recent call last)
in <cell line: 6>()
4 # To use a different branch, change revision
5 # For example: revision="main"
----> 6 model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
7 device_map="auto",
8 trust_remote_code=False,

6 frames
/usr/local/lib/python3.10/dist-packages/auto_gptq/nn_modules/qlinear/qlinear_exllama.py in
12
13 try:
---> 14 from exllama_kernels import make_q4, q4_matmul
15 except ImportError:
16 logger.error('exllama_kernels not installed.')

ImportError: libcudart.so.12: cannot open shared object file: No such file or directory

TheBloke

Owner Nov 9, 2023

•

edited Nov 9, 2023

The default pre-built wheels for 0.5.0 now use PyTorch 2.1 and CUDA 12.1.

If you have CUDA 11.8, you can install AutoGPTQ for PyTorch 2.1 and CUDA 11.8 with:

pip3 uninstall -y auto-gptq
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/

But you'll still need PyTorch 2.1. If you want to use PyTorch 2.0.1, then you can either build AutoGPTQ 0.5.0 from source, or downgrade to AutoGPTQ 0.4.2.

Rohith1016

Nov 9, 2023

•

edited Nov 9, 2023

Thank You for Your Response .

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