Instructions to use KoboldAI/PPO_Pygway-6b-Mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/PPO_Pygway-6b-Mix with Transformers:

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

pipe = pipeline("text-generation", model="KoboldAI/PPO_Pygway-6b-Mix")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/PPO_Pygway-6b-Mix")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/PPO_Pygway-6b-Mix")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KoboldAI/PPO_Pygway-6b-Mix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoboldAI/PPO_Pygway-6b-Mix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/PPO_Pygway-6b-Mix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KoboldAI/PPO_Pygway-6b-Mix

SGLang

How to use KoboldAI/PPO_Pygway-6b-Mix 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 "KoboldAI/PPO_Pygway-6b-Mix" \
    --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": "KoboldAI/PPO_Pygway-6b-Mix",
		"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 "KoboldAI/PPO_Pygway-6b-Mix" \
        --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": "KoboldAI/PPO_Pygway-6b-Mix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/PPO_Pygway-6b-Mix with Docker Model Runner:
```
docker model run hf.co/KoboldAI/PPO_Pygway-6b-Mix
```

Any planes for the future?

by SicariusSicariiStuff - opened Aug 22, 2024

Discussion

SicariusSicariiStuff

Aug 22, 2024

You guys are legends, any plans for new models? and if not, any chance of publishing some of the dataset so we can continue your work?

Henk717

KoboldAI org Aug 22, 2024

This model is old so you could check out our much newer Tiefighter model which is an evolution of some of the models in this one.
I'm also experimenting with a new model more capable of writing tasks and multiple members of our community are publishing merges to.

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