Post
267
What's this cool purple banner haha 😶😶😶
- 3 replies
Jared Sulzdorf PRO
jsulz
AI & ML interests
Infrastructure, law, policy
Recent Activity
liked
a model
about 8 hours ago
bartowski/Tesslate_Tessa-T1-32B-GGUF
Organizations
jsulz's activity
reacted to
clem's
post with 😎
about 7 hours ago
@pabloce you can check it out over here https://huggingface.co/join/xet :)
liked
a
model
about 8 hours ago
updated
a
dataset
2 days ago
updated
a
model
2 days ago
updated
a
dataset
2 days ago
published
a
dataset
2 days ago
updated
a
model
2 days ago
published
a
model
2 days ago
reacted to
clem's
post with 🤗
2 days ago
Post
1450
A repository is created every ~15 secs on Hugging Face so
@kramp
added a "Getting Started" to make it easier & a model release checklist: https://huggingface.co/docs/hub/model-release-checklist
What are you uploading today?
What are you uploading today?
- 1 reply
reacted to
tomaarsen's
post with 🔥
2 days ago
Post
1834
‼️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
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
upvoted
an
article
2 days ago
Article
Training and Finetuning Reranker Models with Sentence Transformers v4
•
62
reacted to
giadap's
post with 🔥
2 days ago
Post
2174
We've all become experts at clicking "I agree" without a second thought. In my latest blog post, I explore why these traditional consent models are increasingly problematic in the age of generative AI.
I found three fundamental challenges:
- Scope problem: how can you know what you're agreeing to when AI could use your data in different ways?
- Temporality problem: once an AI system learns from your data, good luck trying to make it "unlearn" it.
- Autonomy trap: the data you share today could create systems that pigeonhole you tomorrow.
Individual users shouldn't bear all the responsibility, while big tech holds all the cards. We need better approaches to level the playing field, from collective advocacy and stronger technological safeguards to establishing "data fiduciaries" with a legal duty to protect our digital interests.
Available here: https://huggingface.co/blog/giadap/beyond-consent
I found three fundamental challenges:
- Scope problem: how can you know what you're agreeing to when AI could use your data in different ways?
- Temporality problem: once an AI system learns from your data, good luck trying to make it "unlearn" it.
- Autonomy trap: the data you share today could create systems that pigeonhole you tomorrow.
Individual users shouldn't bear all the responsibility, while big tech holds all the cards. We need better approaches to level the playing field, from collective advocacy and stronger technological safeguards to establishing "data fiduciaries" with a legal duty to protect our digital interests.
Available here: https://huggingface.co/blog/giadap/beyond-consent
updated
a
collection
3 days ago
upvoted
a
paper
3 days ago
upvoted
a
collection
5 days ago
upvoted
an
article
7 days ago
Article
The New and Fresh analytics in Inference Endpoints
•
17
liked
a
Space
8 days ago
upvoted
a
collection
9 days ago