🔄 In a Training Loop
Thomas Yiu
legolasyiu
AI & ML interests
Superalignment , alignment, safety LLM, AI, AGI, ASI.
Donation/Funding
https://account.venmo.com/u/Thomas-Yiu
Recent Activity
reacted to danielhanchen's post with 👍 2 days ago
We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU.
Gemma-4-12B NVFP4 works on 11GB VRAM.
26B-A4B hits 13K tok/s (B200).
Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference.
Blog: https://unsloth.ai/docs/basics/nvfp4
Gemma NVFP4: https://huggingface.co/collections/unsloth/nvfp4 updated a model 2 days ago
EpistemeAI/Reasoning-Medical-27B liked a model 3 days ago
mradermacher/Reasoning-Medical-27B-i1-GGUFOrganizations
-
EpistemeAI/Fireball-Llama-3.11-8B-v1orpo
Text Generation • 8B • Updated • 9 -
EpistemeAI/Fireball-Llama-3.11-8B-v2orpo
Text Generation • 8B • Updated • 1 -
EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1-16bit
Text Generation • Updated • 4 • 1 -
EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto
Text Generation • 8B • Updated • 8
-
EpistemeAI/Fireball-Llama-3.11-8B-v1orpo
Text Generation • 8B • Updated • 9 -
EpistemeAI/Fireball-Llama-3.11-8B-v2orpo
Text Generation • 8B • Updated • 1 -
EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1-16bit
Text Generation • Updated • 4 • 1 -
EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto
Text Generation • 8B • Updated • 8