62 lines
1.7 KiB
Markdown
62 lines
1.7 KiB
Markdown
|
---
|
|||
|
|
base_model: Qwen/Qwen3-4B-Instruct-2507
|
|||
|
|
datasets:
|
|||
|
|
- u-10bei/dpo-dataset-qwen-cot
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
license: apache-2.0
|
|||
|
|
library_name: transformers
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
tags:
|
|||
|
|
- dpo
|
|||
|
|
- unsloth
|
|||
|
|
- qwen
|
|||
|
|
- alignment
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# ＜qwen3-4b-dpo-qwen-cot-merged＞
|
|||
|
|
|
|||
|
|
This model is a fine-tuned version of **Qwen/Qwen3-4B-Instruct-2507** using **Direct Preference Optimization (DPO)** via the **Unsloth** library.
|
|||
|
|
|
|||
|
|
This repository contains the **full-merged 16-bit weights**. No adapter loading is required.
|
|||
|
|
|
|||
|
|
## 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
|
|||
|
|
- **Base model**: KazumaTsuboi/LLM_Competition (derived from Qwen/Qwen3-4B-Instruct-2507)
|
|||
|
|
- **Method**: DPO (Direct Preference Optimization)
|
|||
|
|
- **Epochs**: 1
|
|||
|
|
- **Learning rate**: 1e-06
|
|||
|
|
- **Beta**: 0.05
|
|||
|
|
- **Max sequence length**: 1024
|
|||
|
|
- **LoRA Config**: r=16, alpha=16 (merged into base)
|
|||
|
|
|
|||
|
|
## 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]))
|