Instructions to use TehVenom/Pygmalion_AlpacaLora-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TehVenom/Pygmalion_AlpacaLora-7b with Transformers:

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

pipe = pipeline("text-generation", model="TehVenom/Pygmalion_AlpacaLora-7b", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TehVenom/Pygmalion_AlpacaLora-7b")
model = AutoModelForCausalLM.from_pretrained("TehVenom/Pygmalion_AlpacaLora-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TehVenom/Pygmalion_AlpacaLora-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TehVenom/Pygmalion_AlpacaLora-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TehVenom/Pygmalion_AlpacaLora-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TehVenom/Pygmalion_AlpacaLora-7b

SGLang

How to use TehVenom/Pygmalion_AlpacaLora-7b 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 "TehVenom/Pygmalion_AlpacaLora-7b" \
    --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": "TehVenom/Pygmalion_AlpacaLora-7b",
		"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 "TehVenom/Pygmalion_AlpacaLora-7b" \
        --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": "TehVenom/Pygmalion_AlpacaLora-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TehVenom/Pygmalion_AlpacaLora-7b with Docker Model Runner:
```
docker model run hf.co/TehVenom/Pygmalion_AlpacaLora-7b
```

Vicuna 7B

by TornButter - opened May 1, 2023

Discussion

TornButter

May 1, 2023

Thanks for the work you do provided these ready-to-use models! Could you make a Pygmalion-Vicuna-7b using the delta from https://huggingface.co/lmsys/vicuna-7b-delta-v1.1 and the Pygmalion-7b delta? Actually, I don't know if it's possible. Vicuna outperforms Alpaca in 90% of cases: https://vicuna.lmsys.org/

TehVenom

Owner May 1, 2023

•

edited May 1, 2023

Is that vicuna a full fine tune? They are distributed using different methods but it should be possible to have them applied together, I will check it out.

TornButter

May 1, 2023

Sorry, I don't know if it's a full fine tune or not.

TehVenom

Owner May 2, 2023

Enjoy.
https://huggingface.co/TehVenom/Pygmalion-Vicuna-1.1-7b

TornButter

May 2, 2023

Thanks!

TornButter changed discussion status to closed May 2, 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