Instructions to use openaccess-ai-collective/lora-experiments-quant-to-full-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openaccess-ai-collective/lora-experiments-quant-to-full-weights with Transformers:

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

pipe = pipeline("text-generation", model="openaccess-ai-collective/lora-experiments-quant-to-full-weights")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/lora-experiments-quant-to-full-weights")
model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/lora-experiments-quant-to-full-weights", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openaccess-ai-collective/lora-experiments-quant-to-full-weights with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openaccess-ai-collective/lora-experiments-quant-to-full-weights"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openaccess-ai-collective/lora-experiments-quant-to-full-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openaccess-ai-collective/lora-experiments-quant-to-full-weights

SGLang

How to use openaccess-ai-collective/lora-experiments-quant-to-full-weights 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 "openaccess-ai-collective/lora-experiments-quant-to-full-weights" \
    --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": "openaccess-ai-collective/lora-experiments-quant-to-full-weights",
		"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 "openaccess-ai-collective/lora-experiments-quant-to-full-weights" \
        --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": "openaccess-ai-collective/lora-experiments-quant-to-full-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openaccess-ai-collective/lora-experiments-quant-to-full-weights with Docker Model Runner:
```
docker model run hf.co/openaccess-ai-collective/lora-experiments-quant-to-full-weights
```

What model is this?

by Yhyu13 - opened May 21, 2023

Discussion

Yhyu13

May 21, 2023

What model is this based on? And which dataset it is trained on?

winglian

Open Access AI Collective org May 21, 2023

We're just doing some experimentation w LoRA merges to see if they can improve the training efficiency of full weight fine tunes later. Results are inconclusive at the moment as we believe there may be some flaws in training.

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