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", device_map="auto")

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
```

pvduy commited on Apr 28, 2023

Commit

2c8d73c

1 Parent(s): 487b69f

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -29,7 +29,10 @@ python3 apply_delta.py --base /path/to/model_weights/llama-13b --target stable-v
 ## Usage
 Once the delta weights are applied, get started chatting with the model by using the [`transformers`](https://huggingface.co/docs/transformers) library. Following a suggestion from Vicuna Team with Vicuna v0 you should install transformers with this version:
-`pip install git+https://github.com/huggingface/transformers@c612628045822f909020f7eb6784c79700813eda`
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM

 ## Usage
 Once the delta weights are applied, get started chatting with the model by using the [`transformers`](https://huggingface.co/docs/transformers) library. Following a suggestion from Vicuna Team with Vicuna v0 you should install transformers with this version:
+```sh
+pip install git+https://github.com/huggingface/transformers@c612628045822f909020f7eb6784c79700813eda
+```
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM