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

Libraries

How to use CarperAI/stable-vicuna-13b-delta with Transformers:

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

pipe = pipeline("text-generation", model="CarperAI/stable-vicuna-13b-delta")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CarperAI/stable-vicuna-13b-delta")
model = AutoModelForCausalLM.from_pretrained("CarperAI/stable-vicuna-13b-delta")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CarperAI/stable-vicuna-13b-delta with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CarperAI/stable-vicuna-13b-delta

SGLang

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

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

How to combine weights?

by joaomoreno - opened Apr 29, 2023

Discussion

joaomoreno

Apr 29, 2023

The blog post mentions:

Once you have both the weight delta and the LLaMA weights, you can use a script provided in the GitHub repo to combine them and obtain StableVicuna-13B.

What repo is this? Where is the script?

Rbonnav

Apr 29, 2023

•

edited Apr 29, 2023

And why don't they provide directly the full weight???

TheBloke

May 1, 2023

The script to do the delta merge is linked in this model's README, as well as the instructions for doing it.

But I've already done it here: https://huggingface.co/TheBloke/stable-vicuna-13B-HF

So you can just use my merge if you want.

Rbonnav

May 1, 2023

Yes thanks, I am using wour combi ed weight ;)

Kwissbeats

May 6, 2023

I get the following error:
OSError: Unable to load weights from pytorch checkpoint file,
gonna try Blokes solution...

Yhyu13

May 11, 2023

•

edited May 11, 2023

@ALL

I am collecting llama tools, just succeeded in combing this model with original weights provided from https://huggingface.co/decapoda-research/llama-13b-hf/tree/main

Just one caveat thing

CAUTION : you need to replace LLaMATokenier in tokenizer config json into LlamaTokenizer in the original weight repo

A 13B model combo requires about 70GB CPU memory

Here is my llama tool repot : https://gitee.com/yhyu13/llama_-tools

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