Hugging Face's logo
Daniel Fox's picture
84 106 183

Daniel Fox

FlameF0X
Sukmadi's profile picture ninajamy's profile picture zipperzac's profile picture
Ā·
https://flamef0x.github.io

AI & ML interests

Pre-training text generator. (Brother, im 18) Please don't try to contact me.

Recent Activity

published a model less than a minute ago
FlameF0X/GPixelP2
new activity about 6 hours ago
i3-lab/i3-200m-v2:Report
reacted to anakin87's post with ā¤ļø about 12 hours ago
A small model that struggled against a random opponent now beats GPT-5-mini at tic-tac-toe I took https://huggingface.co/LiquidAI/LFM2-2.6B and trained it through play. šŸ§‘ā€šŸ³ Here's how: 1ļøāƒ£ Build a solid RL env with Verifiers (Prime Intellect) 2ļøāƒ£ Generate synthetic data: <200 games sampled from GPT-5-mini playing in the env 3ļøāƒ£ SFT warm-up to teach format 4ļøāƒ£ Group-based RL (CISPO) against opponents making 20-70% random moves 5ļøāƒ£ RL again with stronger opponents (0-25% random moves) + 1.25 temperature to push exploration and shake off suboptimal strategies Done! Beats GPT-5-mini šŸ† --- šŸŽ® Play against the model: https://huggingface.co/spaces/anakin87/LFM2-2.6B-mr-tictactoe šŸ¤— Model: https://huggingface.co/anakin87/LFM2-2.6B-mr-tictactoe šŸ“š Walkthrough/course: https://github.com/anakin87/llm-rl-environments-lil-course šŸ¤— Dataset and checkpoints: https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
View all activity

Organizations

Hugging Face Discord Community's profile picture GoofyLM Lab's profile picture PurrGPT Community's profile picture sha-index's profile picture netgoat-ai's profile picture i3-lab's profile picture anwgpt's profile picture auto-pretrain's profile picture ML intern explorers's profile picture