user: victormustar
897 karma | created 13 years ago
recent submissions
10 days ago|discuss
Zuna: A 380M-parameter foundation model for EEG signals
(huggingface.co)
2 pts|10 days ago|1 comment
10 days ago|discuss
Show HN: Nanbeige 4.1-3B running in the browser via WebGPU
(huggingface.co)
6 pts|10 days ago|2 comments
FinePDFs: Liberating 3T of the finest tokens from PDFs
(huggingface.co)
2 pts|1 month ago|discuss
2 months ago|discuss
Aligning to What? Rethinking Agent Generalization in MiniMax M2
(huggingface.co)
2 pts|2 months ago|discuss
Nvidia Publishes Complete Evaluation Recipe for Nemotron 3 Nano
(huggingface.co)
2 pts|2 months ago|discuss
Using Claude Code to Fine-Tune Open Source LLMs
(huggingface.co)
1 pts|2 months ago|discuss
1 pts|3 months ago|discuss
Porting nanochat to Transformers: an AI modeling history lesson
(huggingface.co)
1 pts|3 months ago|discuss
Kimi-K2-Thinking: open weights LLM with frontier performance
(huggingface.co)
7 pts|3 months ago|discuss
Llama.cpp launches official WebUI for local LLMs
(github.com)
4 pts|3 months ago|discuss
Granite-4.0-Micro: a 3.4B parameter LLM that runs in the browser
(huggingface.co)
4 pts|4 months ago|discuss
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
(jerryliang24.github.io)
1 pts|7 months ago|discuss
How I Use LLMs to Write
(fullydoxxed.com)
20 pts|8 months ago|10 comments
Tiny Agents in Python: an MCP-powered agent in ~70 lines of code
(huggingface.co)
2 pts|9 months ago|discuss
An MCP-powered agent in 50 lines of code
(huggingface.co)
5 pts|9 months ago|discuss
The 4 Things the Qwen-3's Chat Template Teaches Us
(huggingface.co)
2 pts|10 months ago|discuss
2 pts|10 months ago|discuss