Article
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
NormalUhr
• • 292Nicky
NickyNicky
AI & ML interests
None yet
Organizations
upvoted 4
articles 10 months ago
Article
Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs
- +7
wenhuach, Haihao, weiweiz1, n1ck-guo, isaacmac, kding1, IlyasMoutawwakil, marcsun13, medmekk
• • 44 Article
Gemma 3n fully available in the open-source ecosystem!
- +6
ariG23498, pcuenq, sergiopaniego, reach-vb, FL33TW00D-HF, Xenova, Steveeeeeeen, kashif
• • 121 Article
Training and Finetuning Sparse Embedding Models with Sentence Transformers
tomaarsen, arthurbresnu
• • 138 upvoted an article about 1 year ago
Article
Introducing EuroBERT: A High-Performance Multilingual Encoder Model
EuroBERT
• • 147 upvoted a paper about 1 year ago
upvoted 2
articles over 1 year ago
Article
Open R1: Update #2
open-r1
• • 218 Article
wHy DoNt YoU jUsT uSe ThE lLaMa ToKeNiZeR??
catherinearnett
• • 54 upvoted a paper over 1 year ago
upvoted 7
articles over 1 year ago
Article
Open-source DeepResearch – Freeing our search agents
- +3
m-ric, albertvillanova, merve, thomwolf, clefourrier
• • 1.32k Article
Welcome to Inference Providers on the Hub 🔥
- +5
burkaygur, zeke, aton2006, hassanelmghari, sbrandeis, kramp, julien-c
• • 495 Article
The AI tools for Art Newsletter - Issue 1
linoyts, multimodalart
• • 84 Article
The N Implementation Details of RLHF with PPO
- +1
vwxyzjn, tianlinliu0121, lvwerra
• • 72 Article
PEFT: Parameter-Efficient Fine-Tuning Methods for LLMs
samuellimabraz
• • 58 Article
Distributed SFT with trl and DeepSpeed Part 1: Starting Locally
jlzhou
• • 4 Article
We now support VLMs in smolagents!
- +1
m-ric, merve, albertvillanova
• • 113 upvoted a collection over 1 year ago
upvoted 3
articles over 1 year ago
Article
How to Expand Your AI Music Generations of 30 Seconds to Several Minutes
theeseus-ai
• • 3 Article
Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)
ariG23498
• • 50 Article
Fine-tune ModernBERT for RAG with Synthetic Data
sdiazlor
• • 42