Phantomcloak19/TV-CGRPO-Qwen3-4B_no_advantage_adj-QLoRA-TRL
4B • Updated • 14
Rijusmit Biswas
Phantomcloak19
AI & ML interests
Data Science,
Machine Learning,
Deep Learning
Recent Activity
updated a model 9 days ago
Phantomcloak19/TV-CGRPO-Qwen3-4B_no_advantage_adj-QLoRA-TRL published a model 9 days ago
Phantomcloak19/TV-CGRPO-Qwen3-4B_no_advantage_adj-QLoRA-TRL updated a model 9 days ago
Phantomcloak19/TV-CGRPO-Qwen3-4B_no_lagrangian-QLoRA-TRLOrganizations
None yet
Phantomcloak19/TV-CGRPO-Qwen3-4B_no_lagrangian-QLoRA-TRL
4B • Updated • 15
Phantomcloak19/safe-grpo-qlora-Qwen3-4B-long-saftey-grpo-mixed-llm-sources
Text Generation • Updated • 17
Phantomcloak19/TV-CGRPO-Qwen3-4B_no_gating-QLoRA-TRL
4B • Updated • 15
Phantomcloak19/TV-CGRPO-Qwen2-5-3B-Instruct_no_advantage_adj-QLoRA-TRL
3B • Updated • 18
Phantomcloak19/safe-grpo-qlora-Qwen3-4B-long-saftey-grpo-mixed-merged
Text Generation • Updated • 9
Phantomcloak19/TV-CGRPO-Qwen2-5-3B-Instruct_no_lagrangian-QLoRA-TRL
3B • Updated • 14
Phantomcloak19/TV-CGRPO-Qwen2-5-3B-Instruct_no_gating-QLoRA-TRL
3B • Updated • 12
Phantomcloak19/TV-CGRPO-gemma-2-2b-it_no_advantage_adj-QLoRA-TRL
3B • Updated • 15
Phantomcloak19/TV-CGRPO-gemma-2-2b-it_no_lagrangian-QLoRA-TRL
3B • Updated • 8
Phantomcloak19/TV-CGRPO-gemma-2-2b-it_no_gating-QLoRA-TRL
3B • Updated • 16
Phantomcloak19/TV-CGRPO-Qwen3-4B_full-QLoRA-TRL
4B • Updated • 20
Phantomcloak19/SpanBERT-CRF
Updated • 11
Phantomcloak19/safe-grpo-qlora-Qwen2.5-3B-Instruct-long-saftey-grpo-mixed-llm-sources
Text Generation • Updated • 18
Phantomcloak19/safe-grpo-qlora-Qwen2.5-3B-Instruct-long-saftey-grpo-mixed-merged
Text Generation • Updated • 11
Phantomcloak19/TV-CGRPO-Qwen2-5-3B-Instruct_full-QLoRA-TRL
3B • Updated • 15
Phantomcloak19/TV-CGRPO-gemma-2-2b-it_full-QLoRA-TRL
3B • Updated • 18
Phantomcloak19/safe-grpo-qlora-gemma-2-2b-it-long-saftey-grpo-mixed-llm-sources
Text Generation • Updated • 16
Phantomcloak19/safe-grpo-qlora-gemma-2-2b-it-long-saftey-grpo-mixed-merged
Text Generation • Updated • 19
Phantomcloak19/qwen3-dpo-full
Text Generation • 2B • Updated • 28
Phantomcloak19/gemma-dpo-full
Text Generation • 3B • Updated • 14
Phantomcloak19/gemma2-2b-phase2
Text Generation • 3B • Updated • 33 • • 1
Phantomcloak19/qwen3-4b-sft-full
Text Generation • 4B • Updated • 51 •
Phantomcloak19/qwen2.5-3b-sft-full
Text Generation • 3B • Updated • 17
Phantomcloak19/qwen2.5-dpo-overnorm-full
Text Generation • 3B • Updated • 16
Phantomcloak19/qwen2.5-dpo-full
Updated
Phantomcloak19/qwen2.5-1.5b-overnorm-dpo
Updated
Phantomcloak19/whisper-small-hi-final
0.2B • Updated • 2
Phantomcloak19/Qwen2.5_Jailbreak
Text Generation • Updated • 2
Phantomcloak19/LIBRA
Updated