🔄 In a Training Loop

Seth

Sethblocks

P(doom) <0.01%

·

AI & ML interests

Making LLMs FAST, and useful. I enjoy playing with/fine-tuning small models.

Recent Activity

new activity about 17 hours ago

Sethblocks/Andy-Starlight-3B-GGUF:hello model has some issues as it sometimes hallucinates commands sometimes just talks doesnt does its job

updated a model 1 day ago

Sethblocks/Starlight-3B

published a model 1 day ago

Sethblocks/Starlight-3B

View all activity

Organizations

None yet

upvoted a paper about 1 year ago

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Paper • 2504.20571 • Published Apr 29, 2025 • 99

upvoted an article almost 2 years ago

Article

Train a Llama model from scratch

nroggendorff

•

Jul 29, 2024

• 57

upvoted a collection about 2 years ago

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 678

upvoted a collection almost 3 years ago

SDXL ControlNets

7 items • Updated Sep 7, 2023 • 33