Upload 061-arpo_kl-3b_nextgqa-ckpt_418/merges.txt with huggingface_hub 363b7b1 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/preprocessor_config.json with huggingface_hub 4beb6c1 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/special_tokens_map.json with huggingface_hub f227e83 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/model-00001-of-00002.safetensors with huggingface_hub 4e054ec verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/tokenizer_config.json with huggingface_hub 902e326 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/added_tokens.json with huggingface_hub 04853e0 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/generation_config.json with huggingface_hub 5ee26eb verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/model-00002-of-00002.safetensors with huggingface_hub 6fd3876 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/config.json with huggingface_hub 26cfd13 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/model.safetensors.index.json with huggingface_hub 0828c95 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/tokenizer.json with huggingface_hub 35a4d5c verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/chat_template.json with huggingface_hub f7987b6 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/training_args.bin with huggingface_hub 6ffcaae verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/vocab.json with huggingface_hub 69b2676 verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/video_preprocessor_config.json with huggingface_hub f537fae verified CserDu123 commited on Nov 8, 2025
Upload 061-arpo_kl-3b_nextgqa-ckpt_418/trainer_state.json with huggingface_hub 2be4a2f verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/merges.txt with huggingface_hub d54c471 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/preprocessor_config.json with huggingface_hub cb8d2d4 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/special_tokens_map.json with huggingface_hub e61fed1 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/model-00001-of-00004.safetensors with huggingface_hub bb7b6ee verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/tokenizer_config.json with huggingface_hub 542fe03 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/added_tokens.json with huggingface_hub 82ad88b verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/generation_config.json with huggingface_hub 6b7e7cd verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/model-00004-of-00004.safetensors with huggingface_hub a5ce156 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/config.json with huggingface_hub e551d37 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/model-00003-of-00004.safetensors with huggingface_hub 2494fd4 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/model.safetensors.index.json with huggingface_hub 2b41e8b verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/tokenizer.json with huggingface_hub 2ad6536 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/model-00002-of-00004.safetensors with huggingface_hub eefce91 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/chat_template.json with huggingface_hub 5c844a3 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/training_args.bin with huggingface_hub e389423 verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/vocab.json with huggingface_hub c36e88a verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/video_preprocessor_config.json with huggingface_hub 1ea054b verified CserDu123 commited on Nov 8, 2025
Upload 064-arpo_kl-7b-ablation-seed_bench_r1-ckpt_376/trainer_state.json with huggingface_hub 777e066 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/merges.txt with huggingface_hub 69cf2e3 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/preprocessor_config.json with huggingface_hub 0597a8f verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/special_tokens_map.json with huggingface_hub 183bd68 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/model-00001-of-00004.safetensors with huggingface_hub 4d12ea2 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/tokenizer_config.json with huggingface_hub 55d7225 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/added_tokens.json with huggingface_hub 893aa92 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/generation_config.json with huggingface_hub 314632d verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/model-00004-of-00004.safetensors with huggingface_hub 49e180a verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/config.json with huggingface_hub e321b75 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/model-00003-of-00004.safetensors with huggingface_hub 99c6365 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/model.safetensors.index.json with huggingface_hub 628a238 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/tokenizer.json with huggingface_hub 51caa4f verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/model-00002-of-00004.safetensors with huggingface_hub de354aa verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/chat_template.json with huggingface_hub f9d05c2 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/training_args.bin with huggingface_hub 2f69767 verified CserDu123 commited on Nov 8, 2025
Upload 062-arpo_kl-7b-length_reward-seed_bench_r1-ckpt_376/vocab.json with huggingface_hub b9043e1 verified CserDu123 commited on Nov 8, 2025