Gemma-4-E2B-IT fine-tuned on Canvas LMS preference data. SFT, DPO, KTO, IPO, APO-Zero, SPPO, NCA, LoRA, QLoRA. CS3704 v3.0 release.
kleinpanic PRO
kleinpanic93
AI & ML interests
LLMs, NVIDIA-DGX-Spark
Recent Activity
liked a model 10 days ago
thinkingmachines/Inkling liked a model about 2 months ago
Chunjiang-Intelligence/DeepSeek-v4-Fable liked a model about 2 months ago
Qwen/Qwen-AgentWorld-35B-A3BOrganizations
None yet