Instructions to use junelee/wizard-vicuna-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use junelee/wizard-vicuna-13b with Transformers:

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

pipe = pipeline("text-generation", model="junelee/wizard-vicuna-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("junelee/wizard-vicuna-13b")
model = AutoModelForCausalLM.from_pretrained("junelee/wizard-vicuna-13b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use junelee/wizard-vicuna-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "junelee/wizard-vicuna-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "junelee/wizard-vicuna-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/junelee/wizard-vicuna-13b

SGLang

How to use junelee/wizard-vicuna-13b 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 "junelee/wizard-vicuna-13b" \
    --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": "junelee/wizard-vicuna-13b",
		"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 "junelee/wizard-vicuna-13b" \
        --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": "junelee/wizard-vicuna-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use junelee/wizard-vicuna-13b with Docker Model Runner:
```
docker model run hf.co/junelee/wizard-vicuna-13b
```

Dataset issues

by polymer - opened May 7, 2023

Discussion

polymer

May 7, 2023

•

edited May 7, 2023

With some testing using the model, a peculiar issue was found where the model would sometimes output a closing brace (‘}’) after their turn. After looking through the dataset, it appears every conversation has the last turn ended by GPT with a closing brace appended at the end of its response.

For example (last turn, conversation ID AaatApy_0):

[ . . . { "from": "gpt", "value": "The impact of AI . . . opportunities in the years to come.}" } ]

Notice the brace that is erroneously placed inside the string. This issue is present for all conversations in the dataset.

junelee

Owner May 7, 2023

Wow, thanks for the great feedback. We'll make sure to incorporate it in the next version. Thank you 🙏

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