Instructions to use PygmalionAI/pygmalion-1.3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PygmalionAI/pygmalion-1.3b with Transformers:

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

pipe = pipeline("text-generation", model="PygmalionAI/pygmalion-1.3b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PygmalionAI/pygmalion-1.3b")
model = AutoModelForCausalLM.from_pretrained("PygmalionAI/pygmalion-1.3b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PygmalionAI/pygmalion-1.3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PygmalionAI/pygmalion-1.3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PygmalionAI/pygmalion-1.3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PygmalionAI/pygmalion-1.3b

SGLang

How to use PygmalionAI/pygmalion-1.3b 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 "PygmalionAI/pygmalion-1.3b" \
    --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": "PygmalionAI/pygmalion-1.3b",
		"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 "PygmalionAI/pygmalion-1.3b" \
        --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": "PygmalionAI/pygmalion-1.3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PygmalionAI/pygmalion-1.3b with Docker Model Runner:
```
docker model run hf.co/PygmalionAI/pygmalion-1.3b
```

pygmalion-1.3b

Commit History

Jun 26, 2023

05:04
Adding `safetensors` variant of this model⁠

SFconvertbot

d5fb1a8

Jan 11, 2023

23:43
revert KAI chatmode config until related fixes land on stable version

11b

cfe79ad
21:45
enable chat mode by default on KoboldAI

11b

4d2dd2d
05:47
Update README.md

TearGosling

f75fb52

Jan 6, 2023

16:51
I converted this safetensors file wrong and it broke stuff⁠

TearGosling

643274e

Jan 5, 2023

02:08
Add Safetensors file for testing purposes

TearGosling

92c5b18

Jan 4, 2023

23:27
v1.1: new 1.3B model

TearGosling

c276535

Dec 25, 2022

17:54
feat: initial commit

11b

68bd605

Commit History

Jun 26, 2023

Adding `safetensors` variant of this model⁠

Jan 11, 2023

revert KAI chatmode config until related fixes land on stable version

enable chat mode by default on KoboldAI

Update README.md

Jan 6, 2023

I converted this safetensors file wrong and it broke stuff⁠

Jan 5, 2023

Add Safetensors file for testing purposes

Jan 4, 2023

v1.1: new 1.3B model

Dec 25, 2022

feat: initial commit