Trong Vu's picture

6 1 14

Trong Vu

tattrongvu

·

AI & ML interests

LLM, Reinforcement Learning, Robotics, Self-driving car, Computer Vision

Recent Activity

new activity about 2 months ago

tsystems/colqwen2.5-3b-multilingual-v1.0:Has the model also been trained on Italian?

reacted to tomaarsen's post with 🔥 3 months 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!

liked a model 3 months ago

RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16

View all activity

Organizations

Collections 2

models 0

None public yet

datasets 4

tattrongvu/magvit_1m_unlabeled

Viewer • Updated Dec 30, 2024 • 1.25M • 27

tattrongvu/chameleon_1m_unlabeled

Viewer • Updated Dec 30, 2024 • 1.25M • 120

tattrongvu/chameleon_1m

Viewer • Updated Dec 30, 2024 • 1.25M • 30

tattrongvu/magvit_1m

Viewer • Updated Dec 30, 2024 • 1.25M • 33