🏗️ Building on HF

H34v7

h34v7

·

AI & ML interests

Currently focusing on agentic workloads and finetune.

Recent Activity

updated a model 10 days ago

h34v7/LING-3.0-FLASH-ABLITERATED-GGUF

published a model 10 days ago

h34v7/LING-3.0-FLASH-ABLITERATED-GGUF

liked a model 3 months ago

TencentARC/Pixal3D

View all activity

Organizations

None yet

upvoted a collection 4 months ago

🐳 DeepSeek-V4-Distill

3 items • Updated Jul 4 • 10

upvoted 2 papers 4 months ago

Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning

Paper • 2509.24372 • Published Sep 29, 2025 • 16

Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories

Paper • 2602.05085 • Published Feb 4 • 5

upvoted 3 papers 5 months ago

Embarrassingly Simple Self-Distillation Improves Code Generation

Paper • 2604.01193 • Published Apr 1 • 57

Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers

Paper • 2602.06079 • Published Feb 4 • 22

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published Jan 27 • 27