RL-Forgetting-Experiments-3

qwen2.5-3b-kk-sft-ordered-lr1e5-step3175

RL-Forgetting-Experiments-3/qwen2.5-3b-kk-sft-ordered-lr1e5-step3175

qwen2.5-3b-kk-sft-ordered-lr1e5-step3175 is a text generation model from RL-Forgetting-Experiments-3. Use it when you need the model to write or continue text. It is set up for transformers.

Qwen2.5-3B one-epoch SFT checkpoint for the kk ordered arm at optimizer step 3175. Inference-complete, not resumable: all HF model files are present, but the later optimizer/prev-params serialization failed. Those bro…