aquilesfd

aquilesfd's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 22 hours ago

Julia-1.5

Collection

3 items • Updated about 23 hours ago • 7

upvoted a paper 22 days ago

Causal Foundation Models

Paper • 2609.03003 • Published 29 days ago • 30

upvoted 2 collections about 2 months ago

🤏 Smol-Data

Collection

Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated Mar 2 • 21

NAXIUM TUNE

Collection

DO NOT USE - for eventual NAXIUM agentic training • 53 items • Updated 8 days ago • 4

upvoted an article about 2 months ago

view article

Article

DistribAI, a new training framework

• 

Enderchef

•

Aug 2

• 2

upvoted a paper 5 months ago

HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness

Paper • 2605.02396 • Published May 4 • 24

upvoted a collection 5 months ago

DeepSeek-V4

Collection

10 items • Updated 21 days ago • 917

upvoted a paper 6 months ago

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published Mar 19 • 70

upvoted an article 7 months ago

view article

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

• 
• 
• +4

ggerganov, ngxson, allozaur, lysandre, victor, julien-c

•

Feb 20

• 512

upvoted a paper 7 months ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 221

upvoted a collection 8 months ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.79k

upvoted 2 papers 8 months ago

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models

Paper • 2602.04649 • Published Feb 4 • 14

LongCat-Flash-Thinking-2601 Technical Report

Paper • 2601.16725 • Published Jan 23 • 186

upvoted a paper 9 months ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 196

upvoted 2 collections 9 months ago

Jamba2

Collection

Jamba2 is a highly-efficient open source family of language models built for maximum reliability and steerability in the enterprise. • 3 items • Updated Jan 8 • 5

💧 LFM2.5

Collection

Collection of post-trained and base LFM2.5 models. • 16 items • Updated Aug 4 • 229

upvoted a changelog 10 months ago

view changelog

Hugging Face Changelog

HuggingChat for Docs

Dec 12, 2025

• 123

upvoted a paper 11 months ago

MemMamba: Rethinking Memory Patterns in State Space Model

Paper • 2510.03279 • Published Sep 28, 2025 • 74

upvoted a changelog 11 months ago

view changelog

Hugging Face Changelog

Cleaner Collection URLs

Oct 23, 2025

• 84

upvoted a paper 11 months ago

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6, 2025 • 520