V-JEPA 2 Collection A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 4 items • Updated about 13 hours ago • 47
Common Pile v0.1 Filtered Data Collection An LLM pre-training dataset produced by filtering and deduplicating the raw text collected in the Common Pile v0.1 • 31 items • Updated 6 days ago • 12
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text Paper • 2506.05209 • Published 7 days ago • 36
Common Pile v0.1 Raw Data Collection 8TB of public domain and openly licensed text • 30 items • Updated 6 days ago • 12
Common Pile v0.1 Collection All resources related to Common Pile v0.1, an 8TB dataset of public domain and openly licensed text • 4 items • Updated 6 days ago • 24
Falcon-H1 Collection Falcon-H1 Family of Hybrid-Head Language Models, including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained and instruction-tuned). • 37 items • Updated 22 days ago • 40
MedGemma Release Collection Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 4 items • Updated 13 days ago • 158
Qwen3 Collection Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 65 items • Updated 13 days ago • 150
Granite 3.3 Language Models Collection Our latest language models licensed under Apache 2.0 license. • 4 items • Updated May 2 • 34
Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 13 days ago • 197
Rei-12B Collection A small preview of what might become the first(or second?) stepping stone for Magnum v5 • 8 items • Updated May 7 • 4
Llama Nemotron Collection Open, Production-ready Enterprise Models • 8 items • Updated about 10 hours ago • 60