Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
1
3
11
David Miller
lmiller-phdata
Follow
21world's profile picture
1 follower
·
7 following
AI & ML interests
None yet
Recent Activity
reacted
to
tomaarsen
's
post
with ❤️
16 days ago
😎 I just published Sentence Transformers v5.1.0, and it's a big one. 2x-3x speedups of SparseEncoder models via ONNX and/or OpenVINO backends, easier distillation data preparation with hard negatives mining, and more: 1️⃣ Faster ONNX and OpenVINO backends for SparseEncoder models Usage is as simple as `backend="onnx"` or `backend="openvino"` when initializing a SparseEncoder to get started, but I also included utility functions for optimization, dynamic quantization, and static quantization, plus benchmarks. 2️⃣ New `n-tuple-scores` output format from `mine_hard_negatives` This new output format is immediately compatible with the MarginMSELoss and SparseMarginMSELoss for training SentenceTransformer, CrossEncoder, and SparseEncoder losses. 3️⃣ Gathering across devices When doing multi-GPU training using a loss that has in-batch negatives (e.g. MultipleNegativesRankingLoss), you can now use `gather_across_devices=True` to load in-batch negatives from the other devices too! Essentially a free lunch, pretty big impact potential in my evals. 4️⃣ Trackio support If you also upgrade `transformers`, and you install `trackio` with `pip install trackio`, then your experiments will also automatically be tracked locally with trackio. Just open up localhost and have a look at your losses/evals, no logins, no metric uploading. 5️⃣ MTEB Documentation We've added some documentation on evaluating SentenceTransformer models properly with MTEB. It's rudimentary as the documentation on the MTEB side is already great, but it should get you started. Plus many more smaller features & fixes (crash fixes, compatibility with datasets v4, FIPS compatibility, etc.). See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v5.1.0 Big thanks to all of the contributors for helping with the release, many of the features from this release were proposed by others. I have a big list of future potential features that I'd love to add, but I'm
upvoted
an
article
about 2 months ago
The Anthropic Ruling: Why AI Training Just Got Legal (But Piracy Didn't)
upvoted
an
article
5 months ago
Messy Handwriting OCR Comparison Between Aya-Vision-8B and Qwen2VL-OCR-2B
View all activity
Organizations
None yet
lmiller-phdata
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
6 months ago
GSAI-ML/LLaDA-8B-Instruct
Text Generation
•
8B
•
Updated
Feb 27
•
261k
•
310
liked
a dataset
6 months ago
wandb/RAGTruth-processed
Viewer
•
Updated
Nov 28, 2024
•
17.8k
•
727
•
9
liked
3 models
6 months ago
facebook/drama-base
Sentence Similarity
•
0.2B
•
Updated
Jul 21
•
1.87k
•
20
infly/Universal-PRM-7B
Text Generation
•
Updated
Feb 20
•
16
•
7
RLHFlow/Decision-Tree-Reward-Llama-3.1-8B
Text Classification
•
8B
•
Updated
Jan 24
•
9
•
7
liked
a dataset
6 months ago
RLHFlow/LLM-Preferences-HelpSteer2
Viewer
•
Updated
Feb 5
•
9.13k
•
9
•
1
liked
3 models
7 months ago
dleemiller/ModernCE-base-sts
Text Classification
•
0.1B
•
Updated
about 1 month ago
•
610
•
7
dleemiller/ModernCE-large-sts
Text Classification
•
0.4B
•
Updated
Jan 14
•
155
•
1
answerdotai/ModernBERT-large
Fill-Mask
•
0.4B
•
Updated
Jan 15
•
112k
•
419
liked
2 models
8 months ago
answerdotai/ModernBERT-base
Fill-Mask
•
0.1B
•
Updated
Jan 15
•
914k
•
921
stepfun-ai/GOT-OCR2_0
Image-Text-to-Text
•
0.7B
•
Updated
Feb 4
•
70.1k
•
1.51k