Peter Stewart

poita66

·

AI & ML interests

None yet

Recent Activity

reacted to Reubencf's post with 🚀 about 2 months ago

Millions speak Konkani. The internet barely knows it. Today's major LLMs struggle with regional languages. They can't read, write or even recognize Konkani. So I built one that can. Here is a working demo of the Konkani LLM I've been training. 👇 https://youtu.be/8K04ylbXh6k

liked a model 3 months ago

Lorbus/Qwen3.6-27B-int4-AutoRound

liked a model 3 months ago

cyankiwi/Qwen3.6-27B-AWQ-INT4

View all activity

Organizations

None yet

upvoted a changelog 4 months ago

Hugging Face Changelog

Agent Traces on the Hub

Apr 7

• 154

upvoted 4 collections about 1 year ago

Recurrent Models

These are checkpoints for recurrent LLMs developed to scale test-time compute by recurring in latent space. • 15 items • Updated Feb 25 • 12

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 112 items • Updated about 10 hours ago • 785

llama.vim

Recommended models for the llama.vim and llama.vscode plugins • 10 items • Updated 1 day ago • 79

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 10 days ago • 219