15 5

Robert Cicetti

iberob

AI & ML interests

None yet

Recent Activity

published a Space 1 day ago

iberob/nvidia-Llama-3_1-Nemotron-Ultra-253B-v1

liked a Space 2 days ago

reflex-ai/nvidia-Llama-3_1-Nemotron-Ultra-253B-v1-demo

reacted to tomaarsen's post with 🔥 3 days ago

I just released Sentence Transformers v4.1; featuring ONNX and OpenVINO backends for rerankers offering 2-3x speedups and improved hard negatives mining which helps prepare stronger training datasets. Details: 🏎️ ONNX, OpenVINO, Optimization, Quantization - I've added ONNX and OpenVINO support with just one extra argument: "backend" when loading the CrossEncoder reranker, e.g.: `CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2", backend="onnx")` - The `export_optimized_onnx_model`, `export_dynamic_quantized_onnx_model`, and `export_static_quantized_openvino_model` functions now work with CrossEncoder rerankers, allowing you to optimize (e.g. fusions, gelu approximations, etc.) or quantize (int8 weights) rerankers. - I've uploaded ~340 ONNX & OpenVINO models for all existing models under the cross-encoder Hugging Face organization. You can use these without having to export when loading. ⛏ Improved Hard Negatives Mining - Added 'absolute_margin' and 'relative_margin' arguments to `mine_hard_negatives`. - `absolute_margin` ensures that `sim(query, negative) < sim(query, positive) - absolute_margin`, i.e. an absolute margin between the negative & positive similarities. - `relative_margin` ensures that `sim(query, negative) < sim(query, positive) * (1 - relative_margin)`, i.e. a relative margin between the negative & positive similarities. - Inspired by the excellent NV-Retriever paper from NVIDIA. And several other small improvements. Check out the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v4.1.0 With this release, I introduce near-feature parity between the SentenceTransformer embedding & CrossEncoder reranker models, which I've wanted to do for quite some time! With rerankers very strongly supported now, it's time to look forward to other useful architectures!

View all activity

Organizations

None yet

iberob's activity

published a Space 1 day ago

Nvidia-Llama-3 1-Nemotron-Ultra-253B-v1

💬

Chat with a friendly AI assistant

liked a Space 2 days ago

Nvidia Llama 3.1 Nemotron Ultra 253B v1 Demo

🚀

Demo of nvidia-Llama-3_1-Nemotron-Ultra-253B-v1

reacted to tomaarsen's post with 🔥 3 days ago

Post

2482

I just released Sentence Transformers v4.1; featuring ONNX and OpenVINO backends for rerankers offering 2-3x speedups and improved hard negatives mining which helps prepare stronger training datasets. Details:

🏎️ ONNX, OpenVINO, Optimization, Quantization
- I've added ONNX and OpenVINO support with just one extra argument: "backend" when loading the CrossEncoder reranker, e.g.: CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2", backend="onnx")
- The export_optimized_onnx_model, export_dynamic_quantized_onnx_model, and export_static_quantized_openvino_model functions now work with CrossEncoder rerankers, allowing you to optimize (e.g. fusions, gelu approximations, etc.) or quantize (int8 weights) rerankers.
- I've uploaded ~340 ONNX & OpenVINO models for all existing models under the cross-encoder Hugging Face organization. You can use these without having to export when loading.

⛏ Improved Hard Negatives Mining
- Added 'absolute_margin' and 'relative_margin' arguments to mine_hard_negatives.
- absolute_margin ensures that sim(query, negative) < sim(query, positive) - absolute_margin, i.e. an absolute margin between the negative & positive similarities.
- relative_margin ensures that sim(query, negative) < sim(query, positive) * (1 - relative_margin), i.e. a relative margin between the negative & positive similarities.
- Inspired by the excellent NV-Retriever paper from NVIDIA.

And several other small improvements. Check out the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v4.1.0

With this release, I introduce near-feature parity between the SentenceTransformer embedding & CrossEncoder reranker models, which I've wanted to do for quite some time! With rerankers very strongly supported now, it's time to look forward to other useful architectures!