Instructions to use Tandogan/MNLP_M3_dpo_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tandogan/MNLP_M3_dpo_model with Transformers:

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

pipe = pipeline("text-generation", model="Tandogan/MNLP_M3_dpo_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tandogan/MNLP_M3_dpo_model")
model = AutoModelForCausalLM.from_pretrained("Tandogan/MNLP_M3_dpo_model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tandogan/MNLP_M3_dpo_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tandogan/MNLP_M3_dpo_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tandogan/MNLP_M3_dpo_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tandogan/MNLP_M3_dpo_model

SGLang

How to use Tandogan/MNLP_M3_dpo_model 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 "Tandogan/MNLP_M3_dpo_model" \
    --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": "Tandogan/MNLP_M3_dpo_model",
		"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 "Tandogan/MNLP_M3_dpo_model" \
        --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": "Tandogan/MNLP_M3_dpo_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tandogan/MNLP_M3_dpo_model with Docker Model Runner:
```
docker model run hf.co/Tandogan/MNLP_M3_dpo_model
```

Tandogan commited on Jun 9, 2025

Commit

f4d700e

verified ·

1 Parent(s): fe6a9f2

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ DPO lets us directly train the model to score preferred responses higher than le
 - **Optimizer**: AdamW (learning rate = `2e-6`, weight decay = `0`)
 - **Precision**: bf16
 - **Batch size**: 2 (gradient accumulation = 4)
-- **Scheduler**: Linear with 7% warmup
 - **DPO Beta**: 0.1
 - **Eval & Checkpointing**: Every epoch
 - **Monitoring**: Weights & Biases (WandB)

 - **Optimizer**: AdamW (learning rate = `2e-6`, weight decay = `0`)
 - **Precision**: bf16
 - **Batch size**: 2 (gradient accumulation = 4)
+- **Scheduler**: cosine with 1% warmup
 - **DPO Beta**: 0.1
 - **Eval & Checkpointing**: Every epoch
 - **Monitoring**: Weights & Biases (WandB)