Yano Chihiro

yano0

yano0

AI & ML interests

None yet

Recent Activity

liked a model 7 days ago

google/gemma-3-27b-it

upvoted a collection 7 days ago

Ruri v3

reacted to tomaarsen's post with 🔥 20 days ago

‼️Sentence Transformers v4.0 is out! You can now train and finetune reranker models with multi-GPU training, bf16 support, loss logging, callbacks & much more. I also prove that finetuning on your domain helps much more than you might think. 1️⃣ Reranker Training Refactor Reranker models can now be trained using an extensive trainer with a lot of powerful features: - MultiGPU Training (Data Parallelism (DP) and Distributed Data Parallelism (DDP)) - bf16 training support; loss logging - Evaluation datasets + evaluation loss - Improved callback support + an excellent Weights & Biases integration - Gradient checkpointing, gradient accumulation - Model card generation - Resuming from a training checkpoint without performance loss - Hyperparameter Optimization and much more! Read my detailed blogpost to learn about the components that make up this new training approach: https://huggingface.co/blog/train-reranker Notably, the release is fully backwards compatible: all deprecations are soft, meaning that they still work but emit a warning informing you how to upgrade. 2️⃣ New Reranker Losses - 11 new losses: - 2 traditional losses: BinaryCrossEntropy and CrossEntropy - 2 distillation losses: MSE and MarginMSE - 2 in-batch negatives losses: MNRL (a.k.a. InfoNCE) and CMNRL - 5 learning to rank losses: Lambda, p-ListMLE, ListNet, RankNet, ListMLE 3️⃣ New Reranker Documentation - New Training Overview, Loss Overview, API Reference docs - 5 new, 1 refactored training examples docs pages - 13 new, 6 refactored training scripts - Migration guides (2.x -> 3.x, 3.x -> 4.x) 4️⃣ Blogpost Alongside the release, I've written a blogpost where I finetune ModernBERT on a generic question-answer dataset. My finetunes easily outperform all general-purpose reranker models, even models 4x as big. Finetuning on your domain is definitely worth it: https://huggingface.co/blog/train-reranker See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/v4.0.1

View all activity

Organizations

yano0's activity

liked a model 7 days ago

google/gemma-3-27b-it

Image-Text-to-Text • Updated Mar 21 • 656k • • 1.23k

liked a Space 21 days ago

453

2024 AI Timeline

📈

View and filter AI model releases in 2024

liked 2 models 29 days ago

retrieva-jp/amber-large

Feature Extraction • Updated 22 days ago • 98.3k • 7

retrieva-jp/amber-base

Feature Extraction • Updated 22 days ago • 199 • 3

liked a dataset about 1 month ago

facebook/kilt_tasks

Viewer • Updated Jan 4, 2024 • 3.23M • 1.46k • 58

liked 2 datasets 2 months ago

hotchpotch/sentence_transformer_japanese

Viewer • Updated Jan 20 • 13.2M • 772 • 5

sentence-transformers/embedding-training-data

Updated Sep 11, 2024 • 2.12k • 124

liked 3 models 2 months ago

liked a dataset 3 months ago

cl-nagoya/ruri-dataset-v2-pt

Viewer • Updated Jan 14 • 310M • 5.25k • 4

liked a model 3 months ago

hotchpotch/static-embedding-japanese

liked a dataset 3 months ago

Shitao/MLDR

Updated Feb 6, 2024 • 1.59k • 65

liked a model 3 months ago

KoichiYasuoka/modernbert-base-japanese-wikipedia

Fill-Mask • Updated Feb 5 • 64 • 5

liked a dataset 4 months ago

allganize/RAG-Evaluation-Dataset-JA

Viewer • Updated Sep 13, 2024 • 300 • 205 • 23

liked a model 4 months ago

hotchpotch/japanese-splade-v2

Updated Dec 23, 2024 • 1.47k • 12

liked a Space 4 months ago

Japanese Splade Demo Streamlit

📉

Convert text to SPLADE token scores

liked a model 6 months ago

hotchpotch/japanese-splade-base-v1

Updated Dec 23, 2024 • 16 • 8

liked 2 models 7 months ago

dwzhu/e5rope-base

llm-jp/llm-jp-3-172b-beta1

Text Generation • Updated Dec 27, 2024 • 129 • 9