Instructions to use moushi21/dpo-qwen-cot-merged20 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moushi21/dpo-qwen-cot-merged20 with Transformers:

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

pipe = pipeline("text-generation", model="moushi21/dpo-qwen-cot-merged20")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("moushi21/dpo-qwen-cot-merged20")
model = AutoModelForCausalLM.from_pretrained("moushi21/dpo-qwen-cot-merged20")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Local Apps Settings

vLLM

How to use moushi21/dpo-qwen-cot-merged20 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moushi21/dpo-qwen-cot-merged20"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moushi21/dpo-qwen-cot-merged20",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moushi21/dpo-qwen-cot-merged20

SGLang

How to use moushi21/dpo-qwen-cot-merged20 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 "moushi21/dpo-qwen-cot-merged20" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moushi21/dpo-qwen-cot-merged20",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "moushi21/dpo-qwen-cot-merged20" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moushi21/dpo-qwen-cot-merged20",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use moushi21/dpo-qwen-cot-merged20 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for moushi21/dpo-qwen-cot-merged20 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for moushi21/dpo-qwen-cot-merged20 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for moushi21/dpo-qwen-cot-merged20 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="moushi21/dpo-qwen-cot-merged20",
    max_seq_length=2048,
)

Docker Model Runner
How to use moushi21/dpo-qwen-cot-merged20 with Docker Model Runner:
```
docker model run hf.co/moushi21/dpo-qwen-cot-merged20
```

Qwen3-4B-StructEval-Iterative-Alignment

This model is a highly optimized version of Qwen3-4B-Instruct-2507, specifically developed for the StructEval-T task. It features a sophisticated iterative alignment process to maximize performance in structured data reasoning and Chain-of-Thought (CoT) generation.

This repository contains full-merged 16-bit weights. No adapter loading is required.

Training Pipeline

Unlike standard fine-tuning, this model has undergone a four-stage iterative training process to ensure precise alignment and deep reasoning capabilities:

Stage 1: SFT - Foundation building with structured CoT trajectories.
Stage 2: DPO - First alignment to preference reasoning paths.
Stage 3: SFT - Knowledge reinforcement and format refinement.
Stage 4: DPO - Final preference optimization for high-fidelity structured outputs.

Training Objective

The model is engineered to excel in:

Complex Reasoning: Enhanced Chain-of-Thought processing for structural evaluation.
Structural Integrity: Strict adherence to complex data formats (JSON, Tables, etc.).
Consistency: High-reliability outputs across iterative multi-turn interactions.

Training Configuration (Final Stage)

Method: Iterative DPO (Direct Preference Optimization)
Base model: unsloth/Qwen3-4B-Instruct-2507
Epochs: 1
Learning rate: 3e-06
Beta: 0.05
Max sequence length: 2560
Platform: Trained with Unsloth

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "moushi21/dpo-qwen-cot-merged20"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

Sources & Terms (IMPORTANT)

Training data:

u-10bei/structured_data_with_cot_dataset_512_v2
u-10bei/structured_data_with_cot_dataset_512_v4
u-10bei/structured_data_with_cot_dataset_512_v5
u-10bei/structured_data_with_cot_dataset_512
u-10bei/structured_data_with_cot_dataset_v2
u-10bei/structured_data_with_cot_dataset
u-10bei/dpo-dataset-qwen-cot

Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for moushi21/dpo-qwen-cot-merged20

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

unsloth/Qwen3-4B-Instruct-2507

Finetuned

(441)

this model

moushi21
/

dpo-qwen-cot-merged20