agurung/cobalt-ft-qwen3-4b-dpo-mixed-12-mc-correct-v1-lora-r128-a32-lr5e-6-const-lr5e-6-gb64-ep2-beta0p1
Updated
Alexander Gurung PRO
agurung
AI & ML interests
None yet
Recent Activity
published a model about 18 hours 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 about 20 hours 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 about 20 hours 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/cobalt-ft-qwen3-4b-sft-mixed-12-exp-mc-z-v2-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-e
Updated • 34
agurung/cobalt-ft-qwen3-4b-sft-mixed-12-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep2
Updated • 34
agurung/cobalt-ft-qwen3-4b-sft-iid-12-exp-mc-z-v2-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep2
Updated • 24
agurung/cobalt-ft-qwen3-4b-sft-iid-12-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep2
Updated • 33
agurung/cobalt-ft-qwen3-4b-rft-mixed-12-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep2
Updated • 31
agurung/cobalt-ft-qwen3-4b-rft-iid-12-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep2
Updated • 30
agurung/cobalt-ft-qwen3-4b-dpo-mixed-12-mc-raw-v1-lora-r128-a32-lr5e-6-const-lr5e-6-gb64-ep2-beta0p1
Updated • 28
agurung/cobalt-ft-qwen3-4b-dft-mixed-12-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep2
Updated • 26
agurung/cobalt-ft-qwen3-4b-dft-iid-12-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep2
Updated • 32
agurung/lcb-ft-v2-qwen3-4b-rft-mixed-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
Updated • 46
agurung/lcb-ft-v2-qwen3-4b-rft-iid-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
Updated • 54
agurung/lcb-ft-v2-qwen3-4b-dft-mixed-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
Updated • 63
agurung/lcb-ft-v2-qwen3-4b-sft-mixed-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
Updated • 73
agurung/lcb-ft-v2-qwen3-4b-dft-iid-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
Updated • 70
agurung/lcb-ft-v2-qwen3-4b-sft-iid-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4
Updated • 79
agurung/coconut-gemma-3-4b-ff-reward-filtered
Updated
agurung/coconut-qwen3-4b-ff-reward-filtered
Updated
agurung/coconut-gemma-3-1b-gsm-hard
Updated
agurung/flawed-fictions-gemma-3-4b-litereason-sft-positive
5B • Updated • 20
agurung/flawed-fictions-qwen3-4b-litereason-sft-positive
4B • Updated • 4
agurung/colar-gemma-3-1b-gsm-hard-rl
Reinforcement Learning • 1.0B • Updated • 2
agurung/colar-gemma-3-1b-gsm-hard-sft
1.0B • Updated • 5
agurung/colar-gemma-3-4b-ff-sft
4B • Updated • 30
agurung/colar-qwen3-4b-ff-rl
Reinforcement Learning • 4B • Updated • 2
agurung/colar-qwen25-7b-ff-post-rl
Reinforcement Learning • 8B • Updated • 3
agurung/colar-qwen25-7b-ncp-post-rl
Reinforcement Learning • 8B • Updated • 1
agurung/colar-qwen25-7b-ncp-post-sft
8B • Updated • 2
agurung/flawed-fictions-qwen3-4b-litereason
Reinforcement Learning • 4B • Updated • 4
agurung/flawed-fictions-qwen3-4b
Reinforcement Learning • 4B • Updated • 6