Thomas Yiu
legolasyiu
AI & ML interests
Artificial intelligence is, SFT, DPO fine tuning, ORPO fine tuning
Recent Activity
upvoted
a
collection
21 days ago
Gemma 3
updated
a model
25 days ago
EpistemeAI/ReasoningCore-1.0-3B-Instruct-r01-Reflect-Math
liked
a Space
25 days ago
open-llm-leaderboard/comparator
Organizations
Collections
2
-
EpistemeAI/Fireball-Llama-3.11-8B-v1orpo
Text Generation • Updated • 15 -
EpistemeAI/Fireball-Llama-3.11-8B-v2orpo
Text Generation • Updated • 14 -
EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1-16bit
Text Generation • Updated • 10 • 1 -
EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto
Text Generation • Updated • 6 • 8
spaces
15
pinned
Sleeping
R1-distilled leaderboard
⚡
Publish and analyze LLM model performance metrics
pinned
Paused
Video SoundFX
👂
Generates a sound effect that matches video shot
pinned
Runtime error
Video to Music
🎞
Generate and apply matching music background to video shot
pinned
Paused
MusicGen
🎵
pinned
Runtime error
4
MusicGen
🎵
Paused
LGM
🦀