-
Upload folder using huggingface_hub
-
v7 ck1100: GRPO from base_fmt, step 1100/4000 (27.5%), eval-v2 16k: 57.2% MMLU-Pro / 27.8% SuperGPQA / 42.5% overall
-
v7 ck1100: GRPO from base_fmt, step 1100/4000 (27.5%), eval-v2 16k: 57.2% MMLU-Pro / 27.8% SuperGPQA / 42.5% overall
-
Replace grpo_gk with base_fmt: Qwen3-1.7B base + format-forcing chat template (default system prompt + per-question boxed reminder). Zero training. eval-v2 34.7% overall / 50.2% MMLU-Pro (vs grpo_gk 27.0%). Template pre-baked; not re-patched.
-
Push SFT GK model (MMLU 3k + NaturalReasoning 3k, LoRA r=64)
-
Push SFT GK model (MMLU 3k + NaturalReasoning 3k, LoRA r=64)
-
Automated MNLP evaluation report (2026-05-20) (#1)
Nahush-27 +1: zechen-nlp
-
Push SFT GK model (MMLU 3k + NaturalReasoning 3k, LoRA r=64)
-
Add patched chat template: thinking ON + system prompt baked in
-
initial commit
