Downloads · 30 days
19
26% of all-time downloads
yui-math-python-qwen35-9b-v0.6-fft
naksyu/yui-math-python-qwen35-9b-v0.6-fft
yui-math-python-qwen35-9b-v0.6-fft is a text generation model from naksyu. 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.
Full-parameter SFT of Qwen3.5 9B for Korean math/Python reasoning experiments.
All-time downloads
73
Public
Parameters
9B
17.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.9 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026
- SHA
- 961036ea
Base models
Model card
From the Hugging Face model README
Yui Math Python Qwen3.5 9B v0.6 FFT
Full-parameter SFT of Qwen3.5 9B for Korean math/Python reasoning experiments.
Training
- Base model: Qwen/Qwen3.5-9B
- Method: full-parameter bf16 SFT
- Epochs: 1
- Train loss: 0.7942
- Mean token accuracy: 0.8338
- Training tokens: 11.84M
- Hardware: H200 SXM x2
Training Data
Includes Yui/Lime project data plus public Korean reasoning datasets:
- drlee1/deepseek-v4-distill-ko-1k
- Jongsim/claude-opus-4.6-reasoning-12k-ko-filtered-v2
Some upstream data is synthetic or model-generated. This release is experimental.
Intended Use
Research and local inference for Korean math, Python-assisted reasoning, concise calculation behavior, and reasoning-style experiments.
Limitations
Not a general-purpose assistant replacement. Verify arithmetic, code, and factual outputs before relying on them.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_5_text
- License
- apache-2.0
- Languages
- ko, en
- Created
- Jun 28, 2026
- Updated
- Jun 28, 2026