Downloads · 30 days
8
21% of all-time downloads
OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W400
reimu996/OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W400
OneReason-0.8B-Frontier-SFT372-RLOO-DAPO-T12-K1-W400 is a text generation model from reimu996. Use it when you need the model to write or continue text. It is set up for peft.
This repository contains one intermediate LoRA adapter for the Kuaishou LLM4Rec competition.
All-time downloads
38
Public
Repo size
162 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors162 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- e9bdb3e2
Try a prompt
Model card
From the Hugging Face model README
OneReason-0.8B Frontier SFT372 RLOO-DAPO - Window 400
This repository contains one intermediate LoRA adapter for the Kuaishou LLM4Rec competition.
Training
- Start: OneReason-0.8B competition base plus the Frontier SFT step-372 export
- Method: reference-free RLOO with DAPO-style dynamic group filtering
- Completed rollout windows: 400 / 1064
- Completed optimizer updates: 1600 / 4256
- Effective groups per window: 32
- Candidates per prompt: 16
- Sampling temperature: 1.2
- Asymmetric ratio clip: [0.8, 1.28]
- GT anchor / reference model / KL: disabled
- LoRA rank / alpha / dropout: 64 / 64 / 0.0
Files
adapter_model.safetensors: LoRA weightsadapter_config.json: the training checkpoint adapter configuration
The adapter weight SHA256 is
be48da8aed735c063488eabb2c5380f18b6e47c1bda584d335de547f98899cd4.
Evaluation status
This intermediate adapter has not yet received an official competition score. No performance improvement is claimed by this repository.
- Task
- Text Generation
- Library
- peft
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026