Hugging Face's logo

Nomic AI

Enterprise
company
Verified
https://nomic.ai
nomic_ai
nomic-ai
Activity Feed

AI & ML interests

embeddings, graph statistics, nlp

Recent Activity

zpn  published a dataset 1 day ago
nomic-ai/nomic-embed-v2-supervised-data
zpn  updated a dataset 1 day ago
nomic-ai/nomic-embed-v2-supervised-data
tarsur909  authored a paper 2 days ago
VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation
View all activity

nomic-ai's activity

zpn 
published a dataset 1 day ago
zpn 
updated a dataset 1 day ago
tarsur909 
authored 5 papers 2 days ago
zpn 
in nomic-ai/vdr-multilingual-train-hn-mine 3 days ago

Where is the corpus of this dataset?

5
#1 opened 4 days ago by
Haon-Chen
zpn 
updated a collection 3 days ago
zpn 
published a dataset 3 days ago
zpn 
in nomic-ai/nomic-embed-text-v1.5 8 days ago

Could not locate the configuration_hf_nomic_bert.py inside nomic-ai/nomic-bert-2048. Error

9
#25 opened 12 months ago by
Usersh
Cebtenzzre 
updated a model 23 days ago
Cebtenzzre 
in nomic-ai/nomic-embed-text-v2-moe-GGUF 25 days ago

Tokenizer

1
#1 opened 28 days ago by
Zeus0809
Cebtenzzre 
in nomic-ai/nomic-embed-code-GGUF about 1 month ago

Unable to use these with llama.cpp

1
#1 opened about 1 month ago by
circadesu
zpn 
in nomic-ai/nomic-embed-text-v2-moe about 1 month ago

Congratulations on being SOTA in The Arabic RAG Leaderboard

1
#22 opened about 1 month ago by
MohamedRashad
Cebtenzzre 
published a model about 1 month ago
Cebtenzzre 
updated a model about 1 month ago
tomaarsen 
posted an update about 2 months ago
view post
Post
3498
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!
tarsur909 
authored 2 papers 2 months ago