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
```

Exllama not working

#16

by DQ83 - opened Sep 7, 2023

Discussion

DQ83

Sep 7, 2023

•

edited Sep 7, 2023

faulty config.json
these are missing! i inserted all of those but still get an error i cannot sort of. maybe someone knows what the issue is.
"pad_token_id": 0,
"hidden_size": 8192,
"intermediate_size": 22016,
"num_attention_heads": 64,
"num_hidden_layers": 48,
"rms_norm_eps": 1e-05,

errors:
model = ExLlama(config)
device = self.config.device_map.map(key)
raise ValueError("Unknown key: " + key)

DQ83

Sep 7, 2023

the same applies to the WizardCoder Guanaco model @TheBloke

fuzzywuzzy27

Nov 23, 2023

May be related to this.

TheBloke

Owner Nov 24, 2023

•

edited Nov 24, 2023

This model is not compatible with ExLlama. ExLlama only supports Llama models and Llama-derivatives, like Mistral, Yi, Deepseek Coder, etc. Not StarCoder, which is what this model is.

My more recent models have a file table which shows ExLlama compatibility, but I guess I didn't have that when I made this model, and I've not updated the README for it yet. This is a pretty old model now.

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