Downloads · 30 days
0
RationalPursuit/Qwen3-4B-Qwen235B-SFT
Qwen3-4B-Qwen235B-SFT is a text generation model from RationalPursuit. Use it when you need the model to write or continue text. It is set up for peft.
Experimental research artifact. Base: Qwen/Qwen3-4B-Instruct-2507. SFT on rasbt/mathdistill Qwen3-235B-A22B math traces (procedural ≤4000-tok filter). Named -SFT, not -Distill — we SFT'd on a public teacher-trace data…
Downloads · 30 days
0
Access
Public
Updated Jul 13, 2026
Parameters
4B
8.1 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors8 GB · 100%
From the Hugging Face model README
Experimental research artifact. Base: Qwen/Qwen3-4B-Instruct-2507.
SFT on rasbt/math_distill Qwen3-235B-A22B math traces (procedural ≤4000-tok filter). Named -SFT, not -Distill — we SFT'd on a public teacher-trace dataset; we did not run the distillation ourselves.
Eval (MATH-500, 500 anchors): accuracy 325/500 = 0.650; has_think_block 500/500.
Research artifact only — not intended for production use.