Tiny static safety guards: multilabel moderation at wire speed on CPU
Robin Williams
bfuzzy1
AI & ML interests
all of the above.
Recent Activity
new activity about 7 hours ago
rl-llm-wiki/knowledge-base:source: arxiv:2504.14945 — LUFFY (Learning to Reason under Off-Policy Guidance) new activity about 7 hours ago
rl-llm-wiki/knowledge-base:source: arxiv:2405.19107 — DRO (Direct Reward Optimisation / Offline Regularised RL) new activity about 7 hours ago
rl-llm-wiki/knowledge-base:source: arxiv:2501.03262 — REINFORCE++ (critic-free global advantage normalization)Organizations
models 18
bfuzzy1/Railz-Micro
Text Classification • 66.6M • Updated
bfuzzy1/Railz-R2
0.6B • Updated
bfuzzy1/Railz
0.6B • Updated • 35
bfuzzy1/Railz-R
0.6B • Updated • 37
bfuzzy1/TinyGuide
Text Generation • 0.6B • Updated • 40
bfuzzy1/Rodan-Reasoning
Text Generation • 10.4M • Updated • 33
bfuzzy1/Rodan-Chat
Text Generation • 10.4M • Updated • 38
bfuzzy1/Rodan-Base
Text Generation • 11.5M • Updated • 65
bfuzzy1/acheron-m1a-llama
Text Generation • Updated
bfuzzy1/acheron-m
Text Generation • 0.5B • Updated • 4