5 1 14

Trong Vu

tattrongvu

AI & ML interests

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

Recent Activity

reacted to tomaarsen's post with 🔥 8 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!

liked a model 27 days ago

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

updated a Space about 1 month ago

tsystems/visual_document_retrieval

View all activity

Organizations

tattrongvu's activity

liked a model 27 days ago

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

Text Generation • Updated Feb 12 • 9.88k • 32

liked a Space 2 months ago

2.51k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

liked a model 3 months ago

cognitivecomputations/DeepSeek-R1-AWQ

Text Generation • Updated 26 days ago • 9.98k • 77

liked 2 datasets 3 months ago

HuggingFaceM4/Docmatix

Viewer • Updated Aug 26, 2024 • 2.55M • 10.1k • 259

vidore/colpali_train_set

Viewer • Updated Sep 4, 2024 • 119k • 1.89k • 79

liked a model 4 months ago

ByteFlow-AI/TokenFlow

Updated Dec 9, 2024 • 4

liked 5 datasets 4 months ago

liked a dataset 5 months ago

Salesforce/blip3-kale

Viewer • Updated Feb 3 • 235M • 58.6k • 34

liked a model over 1 year ago

deepset/gbert-large

Fill-Mask • Updated Sep 26, 2024 • 4.59k • 56

liked a Space over 1 year ago

174

Mistral-7B-OpenOrca

🌊