Instructions to use QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b")
model = AutoModelForCausalLM.from_pretrained("QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b

SGLang

How to use QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b 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 "QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b" \
    --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": "QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b",
		"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 "QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b" \
        --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": "QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b with Docker Model Runner:
```
docker model run hf.co/QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b
```

Exciting

by Tom9000 - opened Sep 3, 2023

Discussion

Tom9000

Sep 3, 2023

The wait is just killing me..

Tom9000

Sep 4, 2023

•

edited Sep 4, 2023

Thank you so much! Downloading now, only ~5h to go.
Will this be the best model ever? I have a good feeling about this..

Tom9000

Sep 5, 2023

We've got respectable score of 57.36, on huggingface leader board tests, but which is few point lower than many older models and smaller models.
So maybe Code LLama models aren't as good models to start with for finetunes, as many people online make it sound.
From my own few hours of testing yesterday, I too had to admit at the end, "WizardLM-1.0-Uncensored-Llama2-13b" still remains my favorite, for the foreseeable future.

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