Instructions to use openaccess-ai-collective/minotaur-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openaccess-ai-collective/minotaur-13b with Transformers:

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

pipe = pipeline("text-generation", model="openaccess-ai-collective/minotaur-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/minotaur-13b")
model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/minotaur-13b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openaccess-ai-collective/minotaur-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openaccess-ai-collective/minotaur-13b"
# 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/minotaur-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openaccess-ai-collective/minotaur-13b

SGLang

How to use openaccess-ai-collective/minotaur-13b 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/minotaur-13b" \
    --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/minotaur-13b",
		"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/minotaur-13b" \
        --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/minotaur-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openaccess-ai-collective/minotaur-13b with Docker Model Runner:
```
docker model run hf.co/openaccess-ai-collective/minotaur-13b
```

How to use Axolotl?

by ashercn97 - opened Jul 10, 2023

Discussion

ashercn97

Jul 10, 2023

Hi. I have been trying to figure out how to use Axolotl for a bit now and I cannot seem to do it. I have tried deepnote and Google Colab (since my mac isnt good neough to train a model localcly), but every time I get errors. I would love to use Axolotl but I just cannot figure out how. Do you have any tips?

lemonteaa

Jul 30, 2023

You can try again (using colab) I think - seems they've updated axolotl and it should "just work" now (previously when I try you need an extra accelerate config steps that I got stuck on as it's an interactive program :\ ).

Also, a bit of self-promotion - I made a colab notebook to demo the openllama qlora example in their repo: https://github.com/hkitsmallpotato/llm-collections

ashercn97

Jul 31, 2023

Yes! Thank you so much!

ashercn97 changed discussion status to closed Jul 31, 2023

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