31 lines
595 B
Markdown
31 lines
595 B
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
|
|
---
|
|
|
|
# exp033-dpo-wd005-merged
|
|
|
|
SFT + DPO merged model. Full 16-bit weights, no adapter loading required.
|
|
|
|
## Training Pipeline
|
|
1. **SFT**: tomofusa/exp015-blend-h-lora
|
|
2. **DPO**: u-10bei/dpo-dataset-qwen-cot (1 epoch, lr=5e-07, beta=0.1)
|
|
|
|
## DPO Configuration
|
|
- **Learning rate**: 5e-07
|
|
- **Beta**: 0.1
|
|
- **Loss type**: ipo
|
|
- **LoRA**: r=64, alpha=128
|
|
- **Max length**: 1024
|