Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
22
146
676
Aleksei Dorkin
PRO
adorkin
Follow
Tonic's profile picture
ArthurZ's profile picture
shtefcs's profile picture
23 followers
·
84 following
AI & ML interests
Computational Linguistics
Recent Activity
reacted
to
tomaarsen
's
post
with 🔥
about 10 hours 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!
liked
a dataset
about 11 hours ago
TsinghuaC3I/UltraMedical
liked
a dataset
about 11 hours ago
OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B
View all activity
Organizations
adorkin
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
2 datasets
about 11 hours ago
TsinghuaC3I/UltraMedical
Viewer
•
Updated
Apr 28, 2024
•
410k
•
255
•
31
OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B
Viewer
•
Updated
1 day ago
•
200k
•
9
•
32
liked
3 models
about 15 hours ago
shisa-ai/shisa-v2.1-llama3.3-70b
Text Generation
•
1.32M
•
Updated
4 days ago
•
99
•
5
AIDC-AI/Marco-MT-Algharb
Translation
•
15B
•
Updated
Oct 23
•
446
•
25
AIDC-AI/Ovis-Image-7B
Text-to-Image
•
Updated
2 days ago
•
2.58k
•
•
185
liked
a model
1 day ago
llm-jp/Llama-Mimi-8B
Audio-to-Audio
•
8B
•
Updated
Sep 19
•
33
•
9
liked
2 datasets
1 day ago
MaLA-LM/mala-monolingual-split
Viewer
•
Updated
Oct 22
•
825M
•
2.07k
•
4
MathGenie/MathCode-Pile
Viewer
•
Updated
Oct 16, 2024
•
719k
•
4.36k
•
23
liked
a model
1 day ago
Skywork/Skywork-o1-Open-Llama-3.1-8B
Text Generation
•
8B
•
Updated
Aug 29
•
450
•
•
115
liked
a dataset
1 day ago
nvidia/ToolScale
Viewer
•
Updated
15 days ago
•
4.06k
•
2.44k
•
115
liked
4 models
1 day ago
TsinghuaC3I/Llama-3.1-8B-UltraMedical
8B
•
Updated
Sep 10, 2024
•
659
•
14
nvidia/OpenMath2-Llama3.1-8B
Text Generation
•
8B
•
Updated
Nov 25, 2024
•
1.64k
•
•
32
mistralai/Devstral-Small-2-24B-Instruct-2512
24B
•
Updated
1 day ago
•
7.22k
•
267
mistralai/Devstral-2-123B-Instruct-2512
125B
•
Updated
1 day ago
•
2.35k
•
155
liked
4 datasets
5 days ago
CohereLabs/m-ArenaHard-v2.0
Viewer
•
Updated
Jun 27
•
11.5k
•
359
•
5
openai/openai_humaneval
Viewer
•
Updated
Jan 4, 2024
•
164
•
109k
•
357
TalTechNLP/MMLU_et
Viewer
•
Updated
Apr 15
•
14k
•
38
•
2
HiTZ/truthfulqa-multi
Viewer
•
Updated
May 21
•
4.12k
•
1.09k
•
1
liked
a dataset
6 days ago
nvidia/ProfBench
Viewer
•
Updated
Oct 30
•
40
•
497
•
18
liked
a Space
6 days ago
Running
6
ProfBench
🦀
6
Human-annotated rubrics in Professional Tasks
Load more