Instructions to use Rwigle/C-MORAL-Mistral-GDPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Rwigle/C-MORAL-Mistral-GDPO with PEFT:
```
Task type is invalid.
```

How to use Rwigle/C-MORAL-Mistral-GDPO with Transformers:

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

pipe = pipeline("text-generation", model="Rwigle/C-MORAL-Mistral-GDPO")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Rwigle/C-MORAL-Mistral-GDPO", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Rwigle/C-MORAL-Mistral-GDPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Rwigle/C-MORAL-Mistral-GDPO

SGLang

How to use Rwigle/C-MORAL-Mistral-GDPO 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 "Rwigle/C-MORAL-Mistral-GDPO" \
    --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": "Rwigle/C-MORAL-Mistral-GDPO",
		"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 "Rwigle/C-MORAL-Mistral-GDPO" \
        --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": "Rwigle/C-MORAL-Mistral-GDPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rwigle/C-MORAL-Mistral-GDPO with Docker Model Runner:
```
docker model run hf.co/Rwigle/C-MORAL-Mistral-GDPO
```

Link model card to paper and code

by nielsr HF Staff - opened 25 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+16

-24

nielsr

25 days ago

Hi! I'm Niels from the community science team at Hugging Face. This PR improves the model card for the C-MORAL Mistral GDPO adapters.

Key changes include:

Added a direct link to the research paper: C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs.
Added a link to the official GitHub repository.
Included the datasets metadata (NingLab/C-MuMOInstruct) as specified in the training documentation.
Standardized the model description for better readability.

Link model card to paper and codec77d2c40

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment