Article
How to build scalable web apps with OpenAI's Privacy Filter
- +1
ysharma, freddyaboulton, abidlabs
• • 14Parag Ekbote
AINovice2005
AI & ML interests
ML Engineer passionate about taking models from research to production. 1 year supporting tech startups. Active OSS contributor.
Recent Activity
updated a dataset 2 days ago
AINovice2005/raw_benchmark_results_pruna published a dataset 2 days ago
AINovice2005/raw_benchmark_results_pruna updated a dataset 2 days ago
AINovice2005/raw_benchmark_results_hqqOrganizations
upvoted an article about 2 months ago
upvoted a collection 2 months ago
upvoted 3
articles 3 months ago
Article
Ulysses Sequence Parallelism: Training with Million-Token Contexts
kashif, stas
• • 30 Article
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries
- +7
aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego
• • 162 Article
Introducing Storage Buckets on the Hugging Face Hub
- +10
Wauplin, coyotte508, XciD, victor, julien-c, lhoestq, pierric, Sylvestre, hlarcher, rajatarya, seanses, assafvayner
• • 195 upvoted 4
articles 4 months ago
Article
Mixture of Experts (MoEs) in Transformers
- +5
ariG23498, pcuenq, merve, IlyasMoutawwakil, ArthurZ, sergiopaniego, Molbap
• • 167 Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
ggerganov, ngxson, allozaur, lysandre, victor, julien-c
• • 506 Article
Custom Kernels for All from Codex and Claude
- +2
burtenshaw, sayakpaul, ariG23498, evalstate
• • 80 Article
Training Design for Text-to-Image Models: Lessons from Ablations
Photoroom
• • 74 upvoted 2
articles 5 months ago
Article
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
LinkedIn
• • 77 Article
SmolLM-Smashed: Tiny Giants, Optimized for Speed
PrunaAI
• • 15 upvoted a changelog 6 months ago
Hugging Face Changelog
Add a Status to your Hugging Face profile
• 100
upvoted an article 6 months ago
Article
Transformers v5: Simple model definitions powering the AI ecosystem
- +2
lysandre, ArthurZ, cyrilvallez, reach-vb
• • 311 upvoted an article over 1 year ago
Article
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
- +4
medmekk, marcsun13, lvwerra, pcuenq, osanseviero, thomwolf
• • 280