allenai/pixmo-docs
Viewer
•
Updated
•
255k
•
4.39k
•
19
Andrea Gemelli
andreagemelli
AI & ML interests
Natural Language Processing, Computer Vision, Generative Models, Document Analysis
Recent Activity
liked
a dataset
8 days ago
allenai/pixmo-docs
New activity
8 days ago
PleIAs/common_corpus:About document images
liked
a dataset
8 days ago
PleIAs/common_corpus
Organizations
andreagemelli's activity
liked
a
dataset
8 days ago
About document images
#8 opened 8 days ago
by
andreagemelli
andreagemelli
liked
a
dataset
8 days ago
liked
a
model
21 days ago
upvoted
a
paper
22 days ago
upvoted
an
article
29 days ago
Article
Releasing the largest multilingual open pretraining dataset
By
•
•
98
reacted to
tomaarsen's
post with 🔥
about 1 month ago
Post
5171
I just released Sentence Transformers v3.3.0 & it's huge! 4.5x speedup for CPU with OpenVINO int8 static quantization, training with prompts for a free perf. boost, PEFT integration, evaluation on NanoBEIR, and more! Details:
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
export_static_quantized_openvino_model method to quantize a model.2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
prompts argument in SentenceTransformerTrainingArguments. Our experiments show that you can easily reach 0.66% to 0.90% relative performance improvement on NDCG@10 at no extra cost by adding "query: " before each training query and "document: " before each training answer.3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
upvoted
a
paper
3 months ago
upvoted
an
article
7 months ago
Article
Let's talk about LLM evaluation
By
•
•
139
liked
a
model
7 months ago
liked
a
model
10 months ago
liked
a
model
11 months ago
liked
2
Spaces
11 months ago
liked
4
models
11 months ago
liked
a
model
12 months ago
authored
a
paper
over 1 year ago