Upload Qwen3.5-4B rulewise v9 recall final adapter

Upload Qwen3.5-4B rulewise v9 recall checkpoint-3500

Add Qwen3.5-4B rulewise v9 recall-tune README

Upload Qwen3.5-4B rulewise v9 final adapter

Upload Qwen3.5-4B rulewise v9 checkpoint-19000

Upload Qwen3.5-4B rulewise v9 checkpoint-8000

Add Qwen3.5-4B rulewise v9 core backup README

Upload rulewise_resampled_v3recipe_d1_from7000/checkpoint-400/adapter_model.safetensors with huggingface_hub

Upload rulewise_resampled_v3recipe_d1_from7000/checkpoint-400/training_args.bin with huggingface_hub

Upload rulewise_resampled_v3recipe_d1_from7000/checkpoint-400/trainer_state.json with huggingface_hub

Upload rulewise_resampled_v3recipe_d1_from7000/checkpoint-400/adapter_config.json with huggingface_hub

Upload rulewise_rawqwen_v3recipe/checkpoint-1250/adapter_model.safetensors with huggingface_hub

Upload rulewise_rawqwen_v3recipe/checkpoint-1250/training_args.bin with huggingface_hub

Upload rulewise_rawqwen_v3recipe/checkpoint-1250/trainer_state.json with huggingface_hub

Upload rulewise_rawqwen_v3recipe/checkpoint-1250/adapter_config.json with huggingface_hub

upload raw-qwen Run B best eval files checkpoint-1500

upload best eval files for resampled checkpoint-2500

upload best eval file training_args.bin checkpoint 8000

upload best eval file trainer_state.json checkpoint 8000

upload best eval file adapter_model.safetensors checkpoint 8000

upload best eval file adapter_config.json checkpoint 8000

upload eval file training_args.bin checkpoint 7500

upload eval file trainer_state.json checkpoint 7500

upload eval file adapter_model.safetensors checkpoint 7500

upload eval file adapter_config.json checkpoint 7500

upload eval file README.md checkpoint 7000

upload eval file training_args.bin checkpoint 7000

upload eval file trainer_state.json checkpoint 7000

upload eval file adapter_model.safetensors checkpoint 7000

upload eval file adapter_config.json checkpoint 7000

upload eval file README.md checkpoint 6500

upload eval file training_args.bin checkpoint 6500

upload eval file trainer_state.json checkpoint 6500

upload eval file adapter_model.safetensors checkpoint 6500

upload eval file adapter_config.json checkpoint 6500

upload eval file README.md checkpoint 6000

upload eval file training_args.bin checkpoint 6000

upload eval file trainer_state.json checkpoint 6000

upload eval file adapter_model.safetensors checkpoint 6000

upload eval file adapter_config.json checkpoint 6000

Upload continued_checkpoint-1500_from6400

Upload pre_restart_checkpoint-6400

Upload best_eval_loss_checkpoint-5400

Add rulewise weighted checkpoint manifest

Add rulewise weighted checkpoint manifest

Upload vq_casebook_baseline8b_vs_best_20260525_gt_only.zip with huggingface_hub

initial commit