Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Ta1k1
/
sft_Qwen3-32B-DeepMath
like
0
Safetensors
zwhe99/DeepMath-103K
qwen3
Model card
Files
Files and versions
xet
Community
DeepMathを8:2でtrain valに分けてLoRA SFTをした 詳細の設定などは
こちら
を参照
Downloads last month
9
Safetensors
Model size
33B params
Tensor type
BF16
·
Chat template
Files info
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for
Ta1k1/sft_Qwen3-32B-DeepMath
Base model
Qwen/Qwen3-32B
Finetuned
(
159
)
this model
Dataset used to train
Ta1k1/sft_Qwen3-32B-DeepMath
zwhe99/DeepMath-103K
Viewer
•
Updated
May 29
•
103k
•
18.8k
•
284
Collection including
Ta1k1/sft_Qwen3-32B-DeepMath
LLMコンペ2025
Collection
途中過程で実験したやつなど(チームレポジトリ作成前に自分のところにuploadしたものが主なものです)
•
6 items
•
Updated
Oct 16