Instructions to use moreh/MoMo-72B-lora-1.8.6-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moreh/MoMo-72B-lora-1.8.6-DPO with Transformers:

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

pipe = pipeline("text-generation", model="moreh/MoMo-72B-lora-1.8.6-DPO")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("moreh/MoMo-72B-lora-1.8.6-DPO")
model = AutoModelForMultimodalLM.from_pretrained("moreh/MoMo-72B-lora-1.8.6-DPO")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moreh/MoMo-72B-lora-1.8.6-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moreh/MoMo-72B-lora-1.8.6-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moreh/MoMo-72B-lora-1.8.6-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/moreh/MoMo-72B-lora-1.8.6-DPO

SGLang

How to use moreh/MoMo-72B-lora-1.8.6-DPO 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 "moreh/MoMo-72B-lora-1.8.6-DPO" \
    --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": "moreh/MoMo-72B-lora-1.8.6-DPO",
		"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 "moreh/MoMo-72B-lora-1.8.6-DPO" \
        --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": "moreh/MoMo-72B-lora-1.8.6-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use moreh/MoMo-72B-lora-1.8.6-DPO with Docker Model Runner:
```
docker model run hf.co/moreh/MoMo-72B-lora-1.8.6-DPO
```

gguf weight ?

by wukongai - opened Jan 17, 2024

Discussion

wukongai

Jan 17, 2024

Could any expert please help to create the gguf quantified weights for this model? I would be very grateful!

owao

Jan 17, 2024

I bet @TheBloke is already on it ;)

mirek190

Jan 18, 2024

...still waiting for gglm ...

tensorbanana

Jan 19, 2024

@senseable made a q4_k_m.gguf
https://huggingface.co/senseable/MoMo-70B-lora-1.8.6-DPO-gguf

senseable

Jan 19, 2024

@wukongai I'm uploading Q5 and Q6 bits splits now, will probably take over an hour in total

wukongai

Jan 20, 2024

@senseable made a q4_k_m.gguf
https://huggingface.co/senseable/MoMo-70B-lora-1.8.6-DPO-gguf

@wukongai I'm uploading Q5 and Q6 bits splits now, will probably take over an hour in total

Great job! You’ve worked hard! Thank you both for your excellent work!

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