Instructions to use moreh/MoMo-72B-lora-1.8.4-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moreh/MoMo-72B-lora-1.8.4-DPO with Transformers:

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

pipe = pipeline("text-generation", model="moreh/MoMo-72B-lora-1.8.4-DPO")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("moreh/MoMo-72B-lora-1.8.4-DPO")
model = AutoModelForMultimodalLM.from_pretrained("moreh/MoMo-72B-lora-1.8.4-DPO")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moreh/MoMo-72B-lora-1.8.4-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-1.8.4-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-1.8.4-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/moreh/MoMo-72B-lora-1.8.4-DPO

SGLang

How to use moreh/MoMo-72B-lora-1.8.4-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-1.8.4-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-1.8.4-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-1.8.4-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-1.8.4-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use moreh/MoMo-72B-lora-1.8.4-DPO with Docker Model Runner:
```
docker model run hf.co/moreh/MoMo-72B-lora-1.8.4-DPO
```

leejunhyeok commited on Jan 12, 2024

Commit

cbf4acf

verified ·

1 Parent(s): cdfdb55

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -16,8 +16,9 @@ MoMo-70B is trained using **[Moreh](https://moreh.io/)**'s [MoAI platform](https
 - torch
 - peft
 ### Used Datasets
-- Open-Orca/SlimOrca
--
 - No other dataset was used
 - No benchmark test set or the training set are used
   - [data contamination check](https://github.com/swj0419/detect-pretrain-code-contamination) result

 - torch
 - peft
 ### Used Datasets
+- [slimorca](Open-Orca/SlimOrca)
+- [truthy](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1)
+- [orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
 - No other dataset was used
 - No benchmark test set or the training set are used
   - [data contamination check](https://github.com/swj0419/detect-pretrain-code-contamination) result