Hugging Face's logo
Jordan Legg's picture
25 15 56

Jordan Legg PRO

takarajordan
John6666's profile picture Sanjay51's profile picture fuzzy-mittenz's profile picture
Ā·
https://takara.ai

AI & ML interests

Chief AI Officer @takara.ai. Diffusion, Inference optimisation and all things MultiModal.

Recent Activity

reacted to tomaarsen's post with ā¤ļø 7 days ago
šŸ˜Ž I just published Sentence Transformers v5.1.0, and it's a big one. 2x-3x speedups of SparseEncoder models via ONNX and/or OpenVINO backends, easier distillation data preparation with hard negatives mining, and more: 1ļøāƒ£ Faster ONNX and OpenVINO backends for SparseEncoder models Usage is as simple as `backend="onnx"` or `backend="openvino"` when initializing a SparseEncoder to get started, but I also included utility functions for optimization, dynamic quantization, and static quantization, plus benchmarks. 2ļøāƒ£ New `n-tuple-scores` output format from `mine_hard_negatives` This new output format is immediately compatible with the MarginMSELoss and SparseMarginMSELoss for training SentenceTransformer, CrossEncoder, and SparseEncoder losses. 3ļøāƒ£ Gathering across devices When doing multi-GPU training using a loss that has in-batch negatives (e.g. MultipleNegativesRankingLoss), you can now use `gather_across_devices=True` to load in-batch negatives from the other devices too! Essentially a free lunch, pretty big impact potential in my evals. 4ļøāƒ£ Trackio support If you also upgrade `transformers`, and you install `trackio` with `pip install trackio`, then your experiments will also automatically be tracked locally with trackio. Just open up localhost and have a look at your losses/evals, no logins, no metric uploading. 5ļøāƒ£ MTEB Documentation We've added some documentation on evaluating SentenceTransformer models properly with MTEB. It's rudimentary as the documentation on the MTEB side is already great, but it should get you started. Plus many more smaller features & fixes (crash fixes, compatibility with datasets v4, FIPS compatibility, etc.). See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v5.1.0 Big thanks to all of the contributors for helping with the release, many of the features from this release were proposed by others. I have a big list of future potential features that I'd love to add, but I'm
reacted to openfree's post with šŸ”„ 8 days ago
šŸš€ GPT-OSS 120B & 20B - Use Both Models in One Space! https://huggingface.co/spaces/openfree/OpenAI-gpt-oss https://huggingface.co/spaces/VIDraft/gpt-oss-RAG šŸŽÆ Two Models, One Space! GPT-OSS hit #1 on HF just 2 hours after release! šŸ† Now you can use both models conveniently in a single space. šŸ“‹ Model Selection Made Easy! Just pick from the dropdown āœ… ā”œā”€ā”€ GPT-OSS-120B (Complex tasks) ā””ā”€ā”€ GPT-OSS-20B (Quick chats) šŸ’« How to Use (Takes 30 seconds!) Sign in ā†’ With your HF account šŸ” Select model ā†’ Choose what you need šŸ“Œ Apply ā†’ Click! āš” Start chatting ā†’ That's it! šŸ’¬ šŸŒˆ Perfect For: 120B ā†’ Deep analysis, professional work šŸ§  20B ā†’ Fast responses, casual conversations āš” No installation needed - just use it in your browser! šŸŒ āœØ Special Features šŸŽØ Beautiful gradient UI šŸŒ™ Dark mode support šŸ”„ Real-time model switching šŸ†“ Completely free! šŸ‘‰ Try it now! It's really that simple! #GPT-OSS #HuggingFace #FreeAI #EasyToUse
posted an update 8 days ago
What do you all actually think about the open source OpenAI models? Are they legitimately any good or are they hype?
View all activity

Organizations

Social Post Explorers's profile picture Cohere Labs Community's profile picture takara.ai's profile picture Hugging Face Discord Community's profile picture Intelligent Estate's profile picture open/ acc's profile picture Donut Earthers šŸ©'s profile picture