Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
1
1
8
Ankit Dhiman
ankitdhiman
Follow
Mi6paulino's profile picture
thepushkarp's profile picture
pushkar-nurix's profile picture
4 followers
·
8 following
https://ankitdotpy.github.io
ankitdotpy
AI & ML interests
CV, NLP, Speech Anonymization
Recent Activity
updated
a model
14 days ago
ankitdhiman/nero
reacted
to
tomaarsen
's
post
with 🔥
14 days ago
🐦🔥 I've just published Sentence Transformers v5.2.0! It introduces multi-processing for CrossEncoder (rerankers), multilingual NanoBEIR evaluators, similarity score outputs in mine_hard_negatives, Transformers v5 support and more. Details: - CrossEncoder multi-processing: Similar to SentenceTransformer and SparseEncoder, you can now use multi-processing with CrossEncoder rerankers. Useful for multi-GPU and CPU settings, and simple to configure: just `device=["cuda:0", "cuda:1"]` or `device=["cpu"]*4` on the `model.predict` or `model.rank` calls. - Multilingual NanoBEIR Support: You can now use community translations of the tiny NanoBEIR retrieval benchmark instead of only the English one, by passing `dataset_id`, e.g. `dataset_id="lightonai/NanoBEIR-de"` for the German benchmark. - Similarity scores in Hard Negatives Mining: When mining for hard negatives to create a strong training dataset, you can now pass `output_scores=True` to get similarity scores returned. This can be useful for some distillation losses! - Transformers v5: This release works with both Transformers v4 and the upcoming v5. In the future, Sentence Transformers will only work with Transformers v5, but not yet! - Python 3.9 deprecation: Now that Python 3.9 has lost security support, Sentence Transformers no longer supports it. Check out the full changelog for more details: https://github.com/huggingface/sentence-transformers/releases/tag/v5.2.0 I'm quite excited about what's coming. There's a huge draft PR with a notable refactor in the works that should bring some exciting support. Specifically, better multimodality, rerankers, and perhaps some late interaction in the future!
published
a model
26 days ago
ankitdhiman/nero
View all activity
Organizations
None yet
models
5
Sort: Recently updated
ankitdhiman/nero
0.4B
•
Updated
14 days ago
•
42
ankitdhiman/gemma-3-12B-nemotron-it
Any-to-Any
•
12B
•
Updated
Oct 19
•
8
ankitdhiman/ppo-Huggy
Reinforcement Learning
•
Updated
Aug 27
•
40
ankitdhiman/lunar-lander
Reinforcement Learning
•
Updated
Aug 26
•
3
ankitdhiman/nemotron-hinglish-4b-thinking-tool-use
Updated
Aug 26
•
2
datasets
6
Sort: Recently updated
ankitdhiman/colloquial-hinglish-conversations
Viewer
•
Updated
Nov 19
•
2.69k
•
19
•
1
ankitdhiman/nemotron-post-training-dataset-v1-processed
Viewer
•
Updated
Oct 14
•
1.06M
•
269
•
1
ankitdhiman/indicvoices-nanocodec-tokens
Viewer
•
Updated
Oct 6
•
200k
•
51
•
1
ankitdhiman/indicvoice-hi-nanocodec-tokens
Viewer
•
Updated
Oct 4
•
333k
•
17
ankitdhiman/hinglish-conversations
Viewer
•
Updated
Aug 26
•
204k
•
32
•
1
ankitdhiman/haryanvi-tts
Viewer
•
Updated
Aug 12
•
5.52k
•
1.65k
•
2