This dataset is an upsampled version of the original u-10bei/dpo-dataset-qwen-cot dataset. The upsampling was performed to address class imbalance and improve model performance on underrepresented categories.

Key details:

Original dataset: u-10bei/dpo-dataset-qwen-cot
Upsampled dataset: Honejudo1234/dpo-dataset-qwen-cot-upsampled
Modification: Only upsampling (no content modification or data augmentation)
Purpose: Balance training data distribution

Training Objective

This model has been optimized using DPO to align its responses with preferred outputs, focusing on improving reasoning (Chain-of-Thought) and structured response quality based on the provided preference dataset.

Training Configuration

Core Hyperparameters

Parameter	Value
Base Model	Qwen/Qwen3-4B-Instruct-2507
Method	DPO (Direct Preference Optimization)
Learning Rate	5e-07
Beta	0.2
Epochs	1
Max Sequence Length	1024

Batch Size Configuration

Parameter	Value
Per Device Train Batch Size	2
Gradient Accumulation Steps	4
Effective Batch Size	8

Note: The effective batch size is calculated as: Effective Batch Size = per_device_batch_size × gradient_accumulation_steps × num_gpus

LoRA Configuration

Parameter	Value
LoRA Rank (r)	8
LoRA Alpha	16
LoRA Dropout	0
Target Modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Status	Merged into base model (16-bit)

Optimizer Settings

Parameter	Value
Optimizer	OptimizerNames.ADAMW_8BIT
Weight Decay	0.01
Warmup Ratio	0.1

Usage

Since this is a merged model, you can use it directly with transformers.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "your_id/your-repo-name"

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

# Test inference
prompt = "Your question here"
inputs = tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

Sources & License (IMPORTANT)

Original Dataset: u-10bei/dpo-dataset-qwen-cot
Training Dataset (Upsampled): Honejudo1234/dpo-dataset-qwen-cot-upsampled
License: MIT License. (As per dataset terms).
Compliance: Users must follow the original base model's license terms.

Honejudo1234/dpo-qwen-cot-merged_exp09

qwen3-4b-dpo-qwen-cot-upsampled-merged

Dataset