Instructions to use anon8231489123/vicuna-13b-GPTQ-4bit-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anon8231489123/vicuna-13b-GPTQ-4bit-128g with Transformers:

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

pipe = pipeline("text-generation", model="anon8231489123/vicuna-13b-GPTQ-4bit-128g")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anon8231489123/vicuna-13b-GPTQ-4bit-128g")
model = AutoModelForCausalLM.from_pretrained("anon8231489123/vicuna-13b-GPTQ-4bit-128g", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anon8231489123/vicuna-13b-GPTQ-4bit-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anon8231489123/vicuna-13b-GPTQ-4bit-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anon8231489123/vicuna-13b-GPTQ-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g

SGLang

How to use anon8231489123/vicuna-13b-GPTQ-4bit-128g 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 "anon8231489123/vicuna-13b-GPTQ-4bit-128g" \
    --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": "anon8231489123/vicuna-13b-GPTQ-4bit-128g",
		"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 "anon8231489123/vicuna-13b-GPTQ-4bit-128g" \
        --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": "anon8231489123/vicuna-13b-GPTQ-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use anon8231489123/vicuna-13b-GPTQ-4bit-128g with Docker Model Runner:
```
docker model run hf.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g
```

Curious this model able to run on 3060 12g?

#18

by cyx123 - opened Apr 9, 2023

Discussion

cyx123

Apr 9, 2023

Do anyone here own 3060 12g? Can please share some experience about how long does it take to reply a message, need layer to CPU or something even more

CodeExplode

Apr 9, 2023

Yep it runs extremely fast. I've used it with the Oobabooga web-ui.

tamal777

Apr 10, 2023

Yep it runs extremely fast. I've used it with the Oobabooga web-ui.

thank you

JDStephens

Apr 10, 2023

Yep it runs extremely fast. I've used it with the Oobabooga web-ui.

Im running on a 3060ti, but when prompting I'm getting an error that says I have no memory left.

Did you get this error, and if so how did you fix it?
Thanks

tamal777

Apr 10, 2023

Yep it runs extremely fast. I've used it with the Oobabooga web-ui.

Im running on a 3060ti, but when prompting I'm getting an error that says I have no memory left.

Did you get this error, and if so how did you fix it?
Thanks

3060 ti has only 8gb vram. try the 4bit models.

cyx123

Apr 11, 2023

Yep it runs extremely fast. I've used it with the Oobabooga web-ui.

Im running on a 3060ti, but when prompting I'm getting an error that says I have no memory left.

Did you get this error, and if so how did you fix it?
Thanks

add (--pre_layer 11) like i did, i dont know how the numbers works but this pre layer seems to be something like using CPU and gpu at the same time to run the model. imma currently using 1660s...................

star-fire

Apr 12, 2023

Yep it runs extremely fast. I've used it with the Oobabooga web-ui.

Could you please provide me with the application script you are using? Mine will generate self questioning and self answering bugs when used.

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