autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training
autotrust
• • 123Community Blog & Articles
Community Articles
view all
communitychemistryscience
LeMaterial: an open source initiative to accelerate materials discovery and research
- +6
56
December 10, 2024 
awspartnershipscloud
Hugging Face models in Amazon Bedrock
18
December 9, 2024 
text-to-imagedatasetsargilla
Open Preference Dataset for Text-to-Image Generation by the 🤗 Community
- +3
72
December 9, 2024 
multimodalgemmaLLM
Welcome PaliGemma 2 – New vision language models by Google
170
December 5, 2024 
kerasTPUSpaces
How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs
14
December 5, 2024 
leaderboardevaluationnlp
Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard
- +1
39
December 4, 2024 
llmexpert-support-programexpert-support
Investing in Performance: Fine-tune small models with LLM insights - a CFM case study
- +2
43
December 3, 2024 
policyguideethics
Open Source Developers Guide to the EU AI Act
48
December 2, 2024 
dedupestoragecontent addressed store
Rearchitecting Hugging Face Uploads and Downloads
51
November 26, 2024 
multimodalon-devicellm
HotSmolVLM - small yet mighty Vision Language Model
- +1
433
November 26, 2024 
researchmultimodaltutorial
HotYou could have designed state of the art positional encoding
504
November 25, 2024 
communityresearchnlp
Letting Large Models Debate: The First Multilingual LLM Debate Competition
- +8
33
November 20, 2024 
dedupestoragecontent defined chunking
From Files to Chunks: Improving HF Storage Efficiency
76
November 20, 2024 
researchnlpopen-source
Faster Text Generation with Self-Speculative Decoding
67
November 20, 2024 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training
autotrust
• • 123autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model
autotrust
• • 47New in llama.cpp: Decision Models
ggml-org
• • 93LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model
lightonai
• • 26NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
nvidia
• • 88Carbon-A: Finding genes in known and unknown genomes
HuggingFaceBio
• • 20Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance
tiiuae
• • 20Falcon OCR Arabic: 270M Parameters State-of-the-Art Arabic OCR
tiiuae
• • 16Open-sourcing AstaBrief, the fast report-generation model in Asta
allenai
• • 28Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration
FINAL-Bench
• • 12Universal Modder: A Practical Guide to AI Game Modding
a2aprotocol
• • 7Leading the System One Mosaic Benchmark: What Darwin-27B-ZTC-v2's #1 Means
FINAL-Bench
• • 6Uncensor any LLM with abliteration
mlabonne
• • 930KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 428OpenAI Decisions API vs. Jev: A Practical Guide to Decision Models
a2aprotocol
• • 6Decoding LLM Alignment: A Concise Guide for GRPO and its variants
Sneha7
• • 5ViDiHand: The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
Xingang-Pan
• • 4EuroLLM-9B
eurollm-team
• • 144YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research
espnet
• • 36FiftyOne Now Reads LeRobot: 50 Embodiments, 497 Episodes, One Indexed Dataset
harpreetsahota
• • 4