Instructions to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with Transformers:

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

pipe = pipeline("text-generation", model="OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5")
model = AutoModelForCausalLM.from_pretrained("OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5

SGLang

How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 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 "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5" \
    --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": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
		"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 "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5" \
        --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": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with Docker Model Runner:
```
docker model run hf.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
```

Vercel AI SDK

#24

by julianouxui - opened Jul 2, 2023

Discussion

julianouxui

Jul 2, 2023

I'm trying to use the vercel sdk but the application doesn't work and doesn't return an error.
Is anyone having this problem?
in addition to configuring the token in the .env, do you need to configure anything else here?

https://sdk.vercel.ai/docs/guides/huggingface

AvidDabbler

Jul 7, 2023

same

EsoCode

Jul 10, 2023

Not sure, but if the most basic way of loading the model with gradio already gives a error. Then i assum something is not right with it.

import gradio as gr
gr.Interface.load("models/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5").launch()

julianouxui

Aug 16, 2023

i'm use the exemple from github : ai/examples/next-huggingface/app/api/chat
/route.ts , and sucess.
import { HfInference } from '@huggingface/inference'
import { HuggingFaceStream, StreamingTextResponse } from 'ai'
import { experimental_buildOpenAssistantPrompt } from 'ai/prompts'

// Create a new HuggingFace Inference instance
const Hf = new HfInference(process.env.HUGGINGFACE_API_KEY)

// IMPORTANT! Set the runtime to edge
export const runtime = 'edge'

export async function POST(req: Request) {
// Extract the messages from the body of the request
const { messages } = await req.json()

const response = Hf.textGenerationStream({
model: 'OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5',
inputs: experimental_buildOpenAssistantPrompt(messages),
parameters: {
max_new_tokens: 200,
// @ts-ignore (this is a valid parameter specifically in OpenAssistant models)
typical_p: 0.2,
repetition_penalty: 1,
truncate: 1000,
return_full_text: false
}
})

// Convert the response into a friendly text-stream
const stream = HuggingFaceStream(response)

// Respond with the stream
return new StreamingTextResponse(stream)
}

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