Instructions to use pszemraj/bart-large-instructiongen-w-inputs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/bart-large-instructiongen-w-inputs with Transformers:

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

pipe = pipeline("text-generation", model="pszemraj/bart-large-instructiongen-w-inputs")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("pszemraj/bart-large-instructiongen-w-inputs")
model = AutoModelForSeq2SeqLM.from_pretrained("pszemraj/bart-large-instructiongen-w-inputs", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pszemraj/bart-large-instructiongen-w-inputs with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pszemraj/bart-large-instructiongen-w-inputs

SGLang

How to use pszemraj/bart-large-instructiongen-w-inputs 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 "pszemraj/bart-large-instructiongen-w-inputs" \
    --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": "pszemraj/bart-large-instructiongen-w-inputs",
		"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 "pszemraj/bart-large-instructiongen-w-inputs" \
        --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": "pszemraj/bart-large-instructiongen-w-inputs",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pszemraj/bart-large-instructiongen-w-inputs with Docker Model Runner:
```
docker model run hf.co/pszemraj/bart-large-instructiongen-w-inputs
```

How to enable multi-GPU inference?

by bendiu - opened Aug 15, 2023

Discussion

bendiu

Aug 15, 2023

I'm trying to use this on my chunked text docs to generate instruction formatted data for finetuning, but I'm getting this runtimeerror:

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!

Any tips on how to fix this?

pszemraj

Owner Aug 17, 2023

I'm not sure, but also why do you need to do that instead of running in parallel separately on the GPUs? the model is like 1.8 GB. or do you have two 1 GB GPUs??

bendiu

Aug 17, 2023

•

edited Aug 17, 2023

I'm ignorant in parallel and distributed computing. I set the device_map to 'auto' thinking it would speed up inference.

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