Instructions to use samwit/vicuna-13b-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samwit/vicuna-13b-8bit with Transformers:

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

pipe = pipeline("text-generation", model="samwit/vicuna-13b-8bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("samwit/vicuna-13b-8bit")
model = AutoModelForCausalLM.from_pretrained("samwit/vicuna-13b-8bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use samwit/vicuna-13b-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "samwit/vicuna-13b-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "samwit/vicuna-13b-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/samwit/vicuna-13b-8bit

SGLang

How to use samwit/vicuna-13b-8bit 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 "samwit/vicuna-13b-8bit" \
    --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": "samwit/vicuna-13b-8bit",
		"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 "samwit/vicuna-13b-8bit" \
        --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": "samwit/vicuna-13b-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use samwit/vicuna-13b-8bit with Docker Model Runner:
```
docker model run hf.co/samwit/vicuna-13b-8bit
```

Sample code

by iRanadheer - opened Apr 5, 2023

Discussion

iRanadheer

Apr 5, 2023

Hi Sam!

Thanks for creating these models, and I thought it would be better to have a readme file on how to load the model and use it.

devosonder

May 9, 2023

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