23 days ago
-
card: cleanup (structure, status line, support block, dated corrections; measured numbers unchanged)
logic65 +1: Claude Opus 5.5
-
Upload moe/kd_moe_train_v4.py with huggingface_hub
-
Upload moe/kd_moe_train_v3.py with huggingface_hub
-
Upload moe/kd_moe_train_v2.py with huggingface_hub
-
Upload moe/moe27_build.py with huggingface_hub
-
Upload moe/moe27_plan_gen2.pt with huggingface_hub
-
Upload moe/q38_battery2.py with huggingface_hub
-
Upload moe/moe_cluster.py with huggingface_hub
-
Upload moe/antiloop_mix.jsonl with huggingface_hub
-
Upload moe/moe27_plan.py with huggingface_hub
-
Upload moe/moe27_build.py with huggingface_hub
-
Upload moe/moe27_plan.pt with huggingface_hub
-
Upload q38_battery2.py with huggingface_hub
-
Upload battery_kd_colab.py with huggingface_hub
-
Upload generation_config.json with huggingface_hub
-
Upload chat_kd_colab.py with huggingface_hub
-
Upload eval_kd_colab.py with huggingface_hub
-
Upload kd_student_train.py with huggingface_hub
-
Upload chat_template_nothink.jinja with huggingface_hub
-
Upload chat_template.jinja with huggingface_hub
-
Upload kd_student_train.py with huggingface_hub
-
Upload kd_student_train.py with huggingface_hub
-
Upload kd_teacher_pass.py with huggingface_hub
-
Upload kd_teacher_pass.py with huggingface_hub
-
Upload kd_student_train.py with huggingface_hub
-
Upload kd_teacher_pass.py with huggingface_hub
-
Upload a100_sft_tri.py with huggingface_hub
-
Upload data/heal60_mix.jsonl with huggingface_hub
-
Upload README.md with huggingface_hub
-
Upload plans/moe_mask_sidecar.pt with huggingface_hub
-
Upload plans/moe27_plan_s3072.pt with huggingface_hub
-
Upload plans/moe27_plan_s1024.pt with huggingface_hub
-
Upload plans/moe27_plan_s5120.pt with huggingface_hub
-
Upload plans/moe27_plan.pt with huggingface_hub
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Upload README.md with huggingface_hub
-
Upload README.md with huggingface_hub
-
initial commit
