zagreus-0.4B post-trained to 0.4787 on ITALIC (base 0.28, prior leader 0.372) via committee soft answer-KD, under 10 H100h.
Ruggero Marino Lazzaroni
ruggsea
AI & ML interests
NLP in any form
Recent Activity
liked a Space 1 day ago
mii-llm/Post-Training-Challenge updated a collection 2 days ago
ITALIC Post-Training Challenge submission updated a collection 2 days ago
ITALIC Post-Training Challenge submissionOrganizations
spaces 4
Running on Zero
Agents
Philosophy Chat with Llama 3.1
ðŸ’
Chat about philosophy with a knowledgeable AI
Sleeping
Agents
Turing Arena
🤖
Play a game to distinguish human vs AI conversations
Sleeping
Freud Rag
🚀
Prototype for a RAG-enabled Freud chatbot
Sleeping
Agents
1
Demo Gpt-ita-fdi Lega
🦀
models 18
ruggsea/dante-zero-2025-03-05
Text Generation • 0.4B • Updated • 39
ruggsea/reappraisal-bt-reward-model
Updated
ruggsea/qwen3-4b-reappraisal-grpo-v4
Updated
ruggsea/reappraisal-reward-model
2B • Updated • 2
ruggsea/roman-mosaics-lora
Text-to-Image • Updated • 11 • • 1
ruggsea/qwen-2.5-7b-wsdm-cot-continued
Updated • 9
ruggsea/Llama70B-CoT-WSDM-adapter
Updated • 2
ruggsea/Qwen72B-CoT-WSDM-adapter
Updated • 2
ruggsea/Qwen72B-CoT-WSDM
Text Generation • 73B • Updated • 12
ruggsea/Llama70B-CoT-WSDM
Text Generation • 71B • Updated • 9 •
datasets 12
ruggsea/infini-news-index
Updated • 7.49k • 1
ruggsea/infini-news-corpus
Viewer • Updated • 1.36B • 51.4k • 30
ruggsea/social-sim-bench-gens
Viewer • Updated • 1.2k • 1.26k
ruggsea/stanford-encyclopedia-of-philosophy_instruct
Viewer • Updated • 11.9k • 65 • 15
ruggsea/continual-eval
Viewer • Updated • 1.63k • 65
ruggsea/bluesky-journalist-classification
Viewer • Updated • 1.19k • 109 • 1
ruggsea/wsdm2024-deepseek-cot
Viewer • Updated • 55.8k • 48 • 1
ruggsea/wsdm2024-cot-dataset
Viewer • Updated • 48.1k • 24 • 1
ruggsea/stanford-encyclopedia-of-philosophy_chat_multi_turn_mistral_large
Viewer • Updated • 11.9k • 17 • 5
ruggsea/stanford-encyclopedia-of-philosophy_chat_multi_turn_athene
Viewer • Updated • 11.9k • 14 • 2