view article Article Train 400x faster Static Embedding Models with Sentence Transformers 3 days ago β’ 97
The Lessons of Developing Process Reward Models in Mathematical Reasoning Paper β’ 2501.07301 β’ Published 5 days ago β’ 72
O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning Paper β’ 2501.06458 β’ Published 7 days ago β’ 29
view post Post 1758 Famous IC-Light - Relight Images - Advanced Gradio APP with Windows, RunPod, Massed Compute and Free Kaggle Account Installers PublishedInstallers are shared here : https://www.patreon.com/posts/famous-ic-light-1195660711-Click to install and use on Windows, RunPod, Massed Compute and a free Kaggle account notebookAll working perfect with more advanced Gradio app than what was officially published on official repo : https://github.com/lllyasviel/IC-LightMoreover,Started another experimental product training for a client. Doing FLUX Dreambooth / Finetuning via Kohya SS GUI. GPU is L40S and batch size is 7. Config name : Batch_Size_7_48GB_GPU_46250MB_29.1_second_it_Tier_1.jsonFull workflow, step by step tutorial and configs : https://youtu.be/FvpWy1x5etMCheck out the attached images in full resolution fore more info See translation π 4 4 π 3 3 π 2 2 π₯ 1 1 β€οΈ 1 1 π€ 1 1 π 1 1 β 1 1 π§ 1 1 π€― 1 1 π€ 1 1 + Reply
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs Paper β’ 2412.18925 β’ Published 23 days ago β’ 94
view post Post 3037 π DeepSeek πv3 achieves a solid 7 point jump than v2.5, surpassing GPT-4o, but is still behind π o1 πand Claude 3.5. onekq-ai/WebApp1K-models-leaderboard See translation π 6 6 π₯ 6 6 π 1 1 + Reply
view post Post 4662 QwQ can see π₯Qwen team released QvQ, a large vision LM with reasoning π±it outperforms proprietary VLMs on several benchmarks, comes with open weights and a demo! Check them out β¬οΈDemo Qwen/QVQ-72B-previewModel Qwen/QVQ-72B-PreviewRead more https://qwenlm.github.io/blog/qvq-72b-preview/Congratulations @JustinLin610 and team! See translation 2 replies Β· π 12 12 π 8 8 π₯ 6 6 π 4 4 + Reply