Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking Paper • 2609.07379 • Published Sep 10 • 2
ERNIE-5.5-Flash Collection Collection of ERNIE-5.5-Flash models. • 2 items • Updated about 5 hours ago • 21
LFM2.5-24B Harness adapters Collection A collection of models trained with RL on specific adapters for more efficient agentic development • 6 items • Updated 3 days ago • 24
view article Article Welcome Le Chonk: Mistral Large 4 on Hugging Face +9 merve, alvarobartt, ror, cyrilvallez, qgallouedec, ehcalabres, juanjucm, ngxson, pcuenq, burtenshaw, ariG23498 • 7 days ago • 82
Curation decision model: data, recipe, model Collection A 380M curation decision model, its training data (source, labeller, licence per row) and a 1M-page FineWeb example. • 7 items • Updated 7 days ago • 2
view article Article NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt nvidia • 8 days ago • 93
view article Article What's new in the hf CLI and huggingface_hub library huggingface • 10 days ago • 15
Annif models Collection Annif models for text classification and subject indexing. FintoAI prefixed models are in use at Finto AI: https://ai.finto.fi • 8 items • Updated Nov 28, 2025 • 6
LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them Paper • 2610.02076 • Published Oct 4 • 15
Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training Paper • 2608.05148 • Published Aug 5 • 1
view article Article LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model lightonai • 28 days ago • 47
view article Article UltraBERT: One Encoder for Classification and Retrieval dmis-lab • 22 days ago • 66
Jeff 1.0 Collection Jev-style decision models (Gemma 4 and Qwen backbones, 4B to 31B). • 4 items • Updated 6 days ago • 2
Releasing the Inner Jev: A Simple Recipe for Open Decision Models Paper • 2610.17205 • Published 24 days ago • 2
GLiClass-v4 Collection The next generation of zero-shot classifiers. • 3 items • Updated 20 days ago • 11
view article Article NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models nvidia • 15 days ago • 66
Decision models Collection GGUF decision models for the /v1/systemone API in llama.cpp • 16 items • Updated 24 days ago • 41