agurung/Qwen2.5-7B-Instruct-1M-NRL-NCP-GRPO-NLL-UNBOUNDED
Text Generation • 8B • Updated • 107
Alexander Gurung PRO
agurung
AI & ML interests
None yet
Recent Activity
updated a model about 4 hours ago
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-q3c-vs16 updated a model about 4 hours ago
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-q3c-iid16 updated a model 5 days ago
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-q3c-groot16Organizations
agurung/Qwen2.5-7B-Instruct-CONTRASTIVE-NRL-NCP-GRPO-NLL-UNBOUNDED
Text Generation • 8B • Updated • 98
agurung/Qwen2.5-7B-Instruct-CONTRASTIVE-NRL-NCP-GRPO-PPL-UNBOUNDED
Text Generation • 8B • Updated • 95
agurung/Qwen2.5-7B-Instruct-flawedfiction-grpo
Text Generation • 8B • Updated • 91
agurung/qwen7b_LongStory_grpo
Text Generation • 8B • Updated • 85
agurung/Qwen2.5-3B-SFT-LongStoryReasoning
Text Generation • 3B • Updated • 92
agurung/v4_savebestearly_sft_qwen7B_25percent_lr_1e3_bptt_offset
Text Generation • 8B • Updated • 86
agurung/Qwen2.5-7B-Instruct-flawedfiction-latent-grpo-nosft
Text Generation • 8B • Updated • 76
agurung/dft_all_qwen7B_25percent_lr_1e4_allgrad
Text Generation • 8B • Updated • 81
agurung/coconut-gemma-3-4b-ff-reward-filtered
Updated
agurung/Qwen2.5-7B-Instruct-flawedfiction-latent-grpo
Text Generation • 8B • Updated • 83
agurung/flawed-fictions-qwen3-4b
Reinforcement Learning • 4B • Updated • 16
agurung/sft_qwen7B_25percent
Text Generation • 8B • Updated • 80
agurung/flawed-fictions-qwen3-4b-lengthpenalty
Reinforcement Learning • 4B • Updated • 10
agurung/coconut-qwen3-4b-ff-reward-filtered
Updated
agurung/Qwen2.5-7B-Instruct-CONTRASTIVE-NRL-NCP-GRPO-NLL-UNBOUNDED-IMPLICITPROMPT-RPWITHOUTUPDATE
Text Generation • 8B • Updated • 81
agurung/v2sft_qwen7B_25percent_lr_1e4_somegrad
Text Generation • 8B • Updated • 73
agurung/flawed-fictions-gemma-3-4b-lengthpenalty
Reinforcement Learning • 4B • Updated • 10
agurung/v2ff_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset
Text Generation • 8B • Updated • 73
agurung/flawed-fictions-olmo-3-7b
Reinforcement Learning • 7B • Updated • 12
agurung/v2sft_all_qwen7B_25percent_lr_1e6_allgrad
Text Generation • 8B • Updated • 67
agurung/v3ff_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset_newprompt
Text Generation • 8B • Updated • 79
agurung/flawed-fictions-qwen25-7b-lengthpenalty-litereason
Reinforcement Learning • 8B • Updated • 21
agurung/flawed-fictions-gemma-3-4b
Reinforcement Learning • 4B • Updated • 13
agurung/Qwen2.5-7B-Instruct-CONTRASTIVE-NRL-NCP-GRPO-NLL-UNBOUNDED-IMPLICITPROMPT-RPWITHSFT
Text Generation • 8B • Updated • 78
agurung/Qwen2.5-7B-1M-SFT-LongStory
Text Generation • 8B • Updated • 70
agurung/Qwen3-4B-SFT
4B • Updated • 10
agurung/v4_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset
Text Generation • 8B • Updated • 513
agurung/flawed-fictions-qwen25-7b-lengthpenalty
Reinforcement Learning • 8B • Updated • 26
agurung/ncp-qwen25-7b-lengthpenalty
Reinforcement Learning • 8B • Updated • 21