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
```

MNLP M3 DPO Model — Qwen3-0.6B-Base Fine-Tuned with Direct Preference Optimization

This repository contains a Direct Preference Optimization (DPO) model built on top of the base model Qwen/Qwen3-0.6B-Base, as part of the MNLP M3 project. The model is fine-tuned using a high-quality preference dataset to better align responses with human preferences.

Model Description

Base Model: Qwen/Qwen3-0.6B-Base
DPO Dataset: Tandogan/MNLP_M3_dpo_dataset
Libraries: Unsloth, TRL

Training Procedure

Direct Preference Optimization (DPO)

We started from the official Qwen3-0.6B-Base checkpoint and applied Direct Preference Optimization (DPO).
DPO lets us directly train the model to score preferred responses higher than less-preferred ones, using ranked human feedback.

1. From Base Model (`Qwen3-0.6B-Base`)

Dataset: Tandogan/MNLP_M3_dpo_dataset
Max sequence length: 2048 (prompt truncated to 1024)
Epochs: 4
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)
Best Epoch Selection: Based on reward accuracy

Evaluation

Model	BLEU	ROUGE-1/2/L/Lsum	METEOR	MMLU ± SD	TQA_MC1 ± SD	TQA_MC2 ± SD	Reward Acc. ± SD
Qwen3-0.6B-Base	0.1086	0.3282 / 0.1458 / 0.2187 / 0.2964	0.2406	0.5239 ± 0.0365	0.2938 ± 0.0159	0.4589 ± 0.0148	0 ± 0
Qwen3-0.6B	0.0649	0.2488 / 0.0876 / 0.1617 / 0.2224	0.2146	0.4156 ± 0.0361	0.2717 ± 0.0156	0.4284 ± 0.0145	0.4226 ± 0.0088
MNLP M3 DPO Model	0.1343	0.3608 / 0.1634 / 0.2345 / 0.3283	0.2718	0.5264 ± 0.0364	0.3023 ± 0.0161	0.4682 ± 0.0149	0.6997 ± 0.0082

Intended Use

This model is intended for research and experimentation with preference-based alignment and reward modeling.

How to Use

You can use the model with the transformers and trl libraries for inference or evaluation:

from transformers import AutoTokenizer, AutoModelForCausalLM

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

prompt = "Explain recursion in simple terms."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 2

Safetensors

Model size

0.6B params

Tensor type

BF16