Downloads · 30 days
13
11% of all-time downloads
exp031-dpo-toml-custom-merged
tomofusa/exp031-dpo-toml-custom-merged
exp031-dpo-toml-custom-merged is a text generation model from tomofusa. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
SFT + DPO merged model. Full 16-bit weights, no adapter loading required.
All-time downloads
118
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026
- SHA
- 3e202c9c
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
exp031-dpo-toml-custom-merged
SFT + DPO merged model. Full 16-bit weights, no adapter loading required.
Training Pipeline
- SFT: tomofusa/exp015-blend-h-lora
- DPO: tomofusa/llm2025-dpo-blend-031 (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
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026