tattrongvu/DeepSeek-V4-Flash-0731-NVFP4
Text Generation • 304B • Updated • 18 • 1
Trong Vu
tattrongvu
AI & ML interests
LLM, Reinforcement Learning, Robotics, Self-driving car, Computer Vision
Recent Activity
updated a model 3 days ago
tattrongvu/DeepSeek-V4-Flash-0731-NVFP4 published a model 3 days ago
tattrongvu/DeepSeek-V4-Flash-0731-NVFP4 new activity 12 months ago
mrbesher/jina-clip-v2-fi-flickr:Code for fine-tuningOrganizations
updated a
model 3 days ago
published a
model 3 days ago
Code for fine-tuning
2
#1 opened 12 months ago
by tattrongvu
updated a
collection 12 months ago
liked a
dataset 12 months ago
liked a
model about 1 year ago
Has the model also been trained on Italian?
1
#2 opened about 1 year ago
by 
CrisTiru
reacted to tomaarsen's post with 🔥 over 1 year ago
Post
4272
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.:
- The
- 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
-
-
- 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!
🏎️ 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 over 1 year ago
updated a
Space over 1 year ago
updated a
collection over 1 year ago
updated 2
models over 1 year ago
updated a
collection over 1 year ago
updated a
model over 1 year ago
published a
model over 1 year ago
updated a
collection over 1 year ago