James Wright PRO
jsfs11
AI & ML interests
ML engineering, SOTA techniques, LLM fine-tuning and merging
Recent Activity
liked a model 5 days ago
XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash upvoted a paper 14 days ago
Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation upvoted a paper 15 days ago
How LoRA Remembers? A Parametric Memory Law for LLM FinetuningOrganizations
None yet