3 6 16

Emirhan Bilgiç

emirhanbilgic

emirhanbilgic

AI & ML interests

Speech Processing, ML Safety

Recent Activity

liked a model 21 days ago

Collov-Labs/Monetico

liked a Space about 2 months ago

Sycon/CompVis-stable-diffusion-v1-4

updated a model about 2 months ago

emirhanbilgic/paligemma_fine_tuned_test

View all activity

Organizations

None yet

emirhanbilgic's activity

liked a model 21 days ago

Collov-Labs/Monetico

Text-to-Image • Updated 27 days ago • 5.35k • 64

liked a Space about 2 months ago

Runtime error

🐠

emirhanbilgic/paligemma_fine_tuned_test

Updated Oct 1 • 2

liked 2 Spaces about 2 months ago

Running

🤗

Qwen2-VL

Collection

Vision-language model series based on Qwen2 • 15 items • Updated Sep 18 • 157

upvoted a collection 2 months ago

Moshi v0.1 Release

Collection

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated Sep 18 • 218

updated a model 2 months ago

emirhanbilgic/speecht5_finetuned_emirhan_tr

Text-to-Speech • Updated Sep 17 • 124

liked a model 2 months ago

cocktailpeanut/optimus

Text-to-Image • Updated Sep 16 • 149 • • 9

Reacted to tomaarsen's post with 🔥 2 months ago

Post

3710

🚀 Sentence Transformers v3.1 is out! Featuring a hard negatives mining utility to get better models out of your data, a new strong loss function, training with streaming datasets, custom modules, bug fixes, small additions and docs changes. Here's the details:

⛏ Hard Negatives Mining Utility: Hard negatives are texts that are rather similar to some anchor text (e.g. a question), but are not the correct match. They're difficult for a model to distinguish from the correct answer, often resulting in a stronger model after training.
📉 New loss function: This loss function works very well for symmetric tasks (e.g. clustering, classification, finding similar texts/paraphrases) and a bit less so for asymmetric tasks (e.g. question-answer retrieval).
💾 Streaming datasets: You can now train with the datasets.IterableDataset, which doesn't require downloading the full dataset to disk before training. As simple as "streaming=True" in your "datasets.load_dataset".
🧩 Custom Modules: Model authors can now customize a lot more of the components that make up Sentence Transformer models, allowing for a lot more flexibility (e.g. multi-modal, model-specific quirks, etc.)
✨ New arguments to several methods: encode_multi_process gets a progress bar, push_to_hub can now be done to different branches, and CrossEncoders can be downloaded to specific cache directories.
🐛 Bug fixes: Too many to name here, check out the release notes!
📝 Documentation: A particular focus on clarifying the batch samplers in the Package Reference this release.

Check out the full release notes here ⭐: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.1.0

I'm very excited to hear your feedback, and I'm looking forward to the future changes that I have planned, such as ONNX inference! I'm also open to suggestions for new features: feel free to send me your ideas.