modrill/math-think-s1-v2-qwen3-4b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
1 Commit 1 Branch 0 Tags
97e65a964ee22d9a79ecd4cc1e5e7e7a0a712dd5
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE

README.md

library_name, license, base_model, tags
library_name license base_model tags
transformers apache-2.0 Qwen/Qwen3-4B-Base
qwen3
math
sft
llama-factory

math-think-s1-v2-qwen3-4b

Light-R1 stage1 think SFT. cutoff=24576, 2 epoch, lr=1e-5, packing on.

Description
Model synced from source: modrill/math-think-s1-v2-qwen3-4b
Readme 33 KiB
Languages
Jinja 100%