Hugging Face's logo
Timex Peachtree's picture
1 47 217

Timex Peachtree

TimexPeachtree
Gargaz's profile picture Ameeeee's profile picture 0xSojalSec's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a Space 2 days ago
codelion/pts-visualizer
reacted to codelion's post with 🚀 2 days ago
Introducing PTS Visualizer - an interactive tool for exploring how language models reason! Visualize pivotal tokens, thought anchors, and reasoning circuits. See which tokens and sentences significantly impact success probability, explore embedding clusters, and trace reasoning step-by-step. Try it: https://huggingface.co/spaces/codelion/pts-visualizer Explore PTS datasets: - Qwen3-0.6B: https://huggingface.co/datasets/codelion/Qwen3-0.6B-pts - DeepSeek-R1: https://huggingface.co/datasets/codelion/DeepSeek-R1-Distill-Qwen-1.5B-pts Or upload your own JSONL files! GitHub: https://github.com/codelion/pts
reacted to codelion's post with 🚀 2 days ago
Introducing Dhara-70M: A diffusion language model that achieves 3.8x higher throughput than autoregressive models! Key findings from our research on optimal architectures for small language models: → Depth beats width: 32 layers outperforms 12 layers at the same parameter count → Best-in-class factuality: 47.5% on TruthfulQA → 10x training efficiency using WSD (Warmup-Stable-Decay) conversion → Canon layers add only 0.13% parameters but improve reasoning We trained on 1B tokens using the optimal 50-30-20 dataset mix (PDFs + filtered web + educational content), then converted to diffusion with just 100M additional tokens. Blog: https://huggingface.co/blog/codelion/optimal-model-architecture Model: https://huggingface.co/codelion/dhara-70m
View all activity

Organizations

None yet