Instructions to use mayaeary/pygmalion-6b_dev-4bit-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mayaeary/pygmalion-6b_dev-4bit-128g with Transformers:

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

pipe = pipeline("text-generation", model="mayaeary/pygmalion-6b_dev-4bit-128g")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mayaeary/pygmalion-6b_dev-4bit-128g")
model = AutoModelForMultimodalLM.from_pretrained("mayaeary/pygmalion-6b_dev-4bit-128g")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mayaeary/pygmalion-6b_dev-4bit-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mayaeary/pygmalion-6b_dev-4bit-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mayaeary/pygmalion-6b_dev-4bit-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mayaeary/pygmalion-6b_dev-4bit-128g

SGLang

How to use mayaeary/pygmalion-6b_dev-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 "mayaeary/pygmalion-6b_dev-4bit-128g" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mayaeary/pygmalion-6b_dev-4bit-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mayaeary/pygmalion-6b_dev-4bit-128g" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mayaeary/pygmalion-6b_dev-4bit-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mayaeary/pygmalion-6b_dev-4bit-128g with Docker Model Runner:
```
docker model run hf.co/mayaeary/pygmalion-6b_dev-4bit-128g
```

Need help loading the model

by ArabianShark - opened Nov 27, 2023

Discussion

ArabianShark

Nov 27, 2023

I've not managed to load the model in Oobabooga's Text Generation web UI.

For one thing, I don't know which loader to use. I've tried them all, but they've each found an error (not always a new error), and none managed to load the model, leading me to believe I may need to fidget with the loader settings as well. Found errors include " 'hidden_size'", "At least one of the model submodule will be offloaded to disk, please pass along an offload_folder" and "Trying to set a tensor of shape torch.Size([32, 512]) in "qzeros" (which has shape torch.Size([1, 512])), this look incorrect."

Any help would be much appreciated!

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