agurung/colar-qwen25-7b-ff-post-sft
8B • Updated
Alexander Gurung PRO
agurung
AI & ML interests
None yet
Recent Activity
published a model 2 days ago
agurung/cobalt-ft-qwen3-4b-dpo-mixed-12-mc-correct-v1-lora-r128-a32-lr5e-6-const-lr5e-6-gb64-ep2-beta0p1 updated a model 2 days ago
agurung/cobalt-ft-qwen3-4b-sft-mixed-12-exp-mc-z-v2-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-e published a model 2 days ago
agurung/cobalt-ft-qwen3-4b-sft-mixed-12-exp-mc-z-v2-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-eOrganizations
agurung/qwen-coconut-ff-v2
8B • Updated • 1
agurung/ncp-qwen25-7b-lengthpenalty
Reinforcement Learning • 8B • Updated
agurung/flawed-fictions-qwen3-4b-lengthpenalty-litereason
Reinforcement Learning • 4B • Updated • 1
agurung/colar-qwen3-4b-ff-sft
4B • Updated
agurung/flawed-fictions-gemma-3-4b-lengthpenalty
Reinforcement Learning • 4B • Updated • 1
agurung/flawed-fictions-qwen3-4b-lengthpenalty
Reinforcement Learning • 4B • Updated • 3
agurung/qwen3-4b-ff-grpo-lengthpenalty
4B • Updated • 2
agurung/colar-ff-qwen3-4b
4B • Updated • 1
agurung/flawed-fictions-qwen25-7b-lengthpenalty-litereason
Reinforcement Learning • 8B • Updated • 2
agurung/flawed-fictions-qwen25-7b-lengthpenalty
Reinforcement Learning • 8B • Updated • 1
agurung/flawed-fictions-olmo-3-7b
Reinforcement Learning • 7B • Updated • 2
agurung/flawed-fictions-gemma-3-4b
Reinforcement Learning • 4B • Updated • 5
agurung/qwen3-4b-lcb-dapo-correctness
Updated
agurung/Qwen2.5-7B-Instruct-flawedfiction-latent-grpo
Text Generation • 8B • Updated • 15
agurung/v4_savebestearly_sft_qwen7B_25percent_lr_1e3_bptt_offset
Text Generation • 8B • Updated • 2
agurung/v4_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset
Text Generation • 8B • Updated • 3
agurung/v3sft_qwen7B_25percent_lr_1e4_bptt_offset
Text Generation • 8B • Updated • 3
agurung/v1ff_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset
Text Generation • 8B • Updated • 2
agurung/v2ff_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset
Text Generation • 8B • Updated • 3
agurung/v3ff_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset_newprompt
Text Generation • 8B • Updated • 9
agurung/Qwen2.5-7B-Instruct-flawedfiction-latent-grpo-nosft
Text Generation • 8B • Updated • 2
agurung/olmo3-7b-lcb-mc-nosum-gspo
Updated
agurung/olmo3-7b-lcb-mc-gspo
Updated
agurung/olmo3-7b-lcb-standard-rl-gspo
Updated
agurung/olmo3-7b-lcb-mc-rl
Updated
agurung/olmo3-7b-lcb-standard-rl
Reinforcement Learning • Updated
agurung/qwen34b-context-kd
Text Generation • 4B • Updated • 1
agurung/Qwen2.5-7B-Instruct-flawedfiction-grpo-impdata
Text Generation • 8B • Updated • 3
agurung/Qwen2.5-7B-Instruct-flawedfiction-grpo
Text Generation • 8B • Updated • 7