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
```

config.json paramaters

by Nexesenex - opened Sep 4, 2023

Discussion

Nexesenex

Sep 4, 2023

•

edited Sep 4, 2023

On this model, it reads :

"max_position_embeddings": 2048,
"torch_dtype": "float16",

Shouldn't it be like on the original CodeLlama model and Airoboros c34b 2.1?

"max_position_embeddings": 16384,
"torch_dtype": "bfloat16",

Also, wouldn't "rope_theta": 1000000, be useful, as per the original CodeLlama model?

Thanks for publishing this, as well as for Samantha C34 1.11 (who is a real challenge for context obedient prompt and model schizophrenia between the Assistant and the Character Samantha), Eric!

ehartford

Quixi AI org Sep 5, 2023

I didn't set any of those values. I used CodeLlama as the base model

TheBloke

Sep 5, 2023

•

edited Sep 5, 2023

From where? Did you use a non-official source perhaps? The correct values are here: https://huggingface.co/codellama/CodeLlama-34b-hf/blob/main/config.json

It should have 16K and rope_theta 1M yeah. I'll change it for my quants and I put in a PR

ehartford

Quixi AI org Sep 5, 2023

Thank you Tom

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