Active filters: agurung
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-base-q3c
Text Generation
• 4B • Updated • 5.63k
• 1
agurung/iron-march-roberta
Fill-Mask
• Updated • 9
agurung/character_sheet_entailment_model___mistral7bv2
Text Generation
• 7B • Updated • 15
agurung/model_output_dir_storysummary_newlossv0
Updated
agurung/model_output_dir_storysummary_toplotsummary_newlossv0
Updated
3B • Updated • 14
agurung/Qwen2.5-3B-SFT-LongStoryReasoning
Text Generation
• 3B • Updated • 92
agurung/LongStory-Qwen2.5-3B-SFT
Updated
agurung/qwen3b_LongStory_grpo
Updated
agurung/Qwen2.5-7B-1M-SFT-LongStory
Text Generation
• 8B • Updated • 70
agurung/qwen7b_LongStory_grpo
Text Generation
• 8B • Updated • 85
4B • Updated • 10
agurung/Qwen2.5-7B-Instruct-1M-NRL-NCP-GRPO-NLL-UNBOUNDED
Text Generation
• 8B • Updated • 107
agurung/Qwen2.5-7B-Instruct-1M-NRL-NCP-GRPO-NLL-PIECEWISE-REWARD
Text Generation
• 8B • Updated • 115
agurung/Qwen3-8B-SFT-No-Vocab-Projection
8B • Updated • 16
agurung/v2Qwen3-8B-SFT-No-Vocab-Projection
8B • Updated • 15
agurung/v3Qwen3-8B-SFT-No-Vocab-Projection
8B • Updated • 16
agurung/SweepQwen2.5-3B-SFT-LongStory
Updated
agurung/Qwen2.5-7B-Instruct-1M-NRL-NCP-GRPO-NLL-PIECEWISE-REWARD_20ep
Text Generation
• 8B • Updated • 13
agurung/Qwen2.5-7B-Instruct-1M-NRL-NCP-GRPO-PPL-UNBOUNDED
Text Generation
• 8B • Updated • 14
agurung/v4Qwen3-8B-SFT-No-Vocab-Projection-Implicit-Thought
Updated
Text Generation
• 8B • Updated • 14
agurung/sft_qwen7B_25percent
Text Generation
• 8B • Updated • 80
agurung/sft_qwen8B_25percent
Text Generation
• 8B • Updated • 154
agurung/sft_qwen8B_25percent_lr_1e4
Text Generation
• 8B • Updated • 10
agurung/sft_qwen7B_25percent_lr_1e4_allgrad
Text Generation
• 8B • Updated • 13
agurung/sft_qwen8B_25percent_lr_1e4_allgrad
Updated
agurung/sft_qwen7B_25percent_lr_1e4_somegrad
Text Generation
• 8B • Updated • 188
agurung/v2sft_qwen7B_25percent_lr_1e4_somegrad
Text Generation
• 8B • Updated • 73