amazon-sagemaker-community (Amazon SageMaker Community)

posted an update 6 days ago

Post

2283

Quite excited by the ModernBERT release! 0.15/0.4B small, 2T modern pre-training data and tokenizer with code, 8k context window, great efficient model for embeddings & classification!

This will probably be the basis for many future SOTA encoders! And I can finally stop using DeBERTav3 from 2021 :D

Congrats @answerdotai , @LightOnIO and collaborators like @tomaarsen !

Paper and models here 👇https://huggingface.co./collections/answerdotai/modernbert-67627ad707a4acbf33c41deb

MoritzLaurer

posted an update 9 days ago

Post

1017

"Open-source AI: year in review 2024": amazing Space with lots of data-driven insights into AI in 2024! Check it out 👇
huggingface/open-source-ai-year-in-review-2024

2 replies

·

MoritzLaurer

posted an update 14 days ago

Post

1264

I've been building a small library for working with prompt templates on the HF hub: pip install prompt-templates. Motivation:

The community currently shares prompt templates in a wide variety of formats: in datasets, in model cards, as strings in .py files, as .txt/.yaml/.json/.jinja2 files etc. This makes sharing and working with prompt templates unnecessarily complicated.

Prompt templates are currently the main hyperparameter that people tune when building complex LLM systems or agents. If we don't have a common standard for sharing them, we cannot systematically test and improve our systems. After comparing different community approaches, I think that working with modular .yaml or .json files is the best approach.

The prompt-templates library :
- proposes a standard for sharing prompts (entirely locally or on the HF hub)
- provides some utilities that are interoperable with the broader ecosystem

Try it:

# !pip install prompt-templates
from prompt_templates import PromptTemplateLoader 
prompt_template = PromptTemplateLoader.from_hub(repo_id="MoritzLaurer/closed_system_prompts", filename="claude-3-5-artifacts-leak-210624.yaml")

The library is in early stages, feedback is welcome!

More details in the docs: https://github.com/MoritzLaurer/prompt_templates/

1 reply

·

DrishtiSharma

authored a paper 14 days ago

1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering

Paper • 2412.06009 • Published 17 days ago

DrishtiSharma

authored a paper 15 days ago

Maya: An Instruction Finetuned Multilingual Multimodal Model

Paper • 2412.07112 • Published 16 days ago • 25

julien-c

posted an update 15 days ago

Post

7612

After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co./docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥

cc: @reach-vb @pierric @victor and the HF team

28 replies

·

DrishtiSharma

authored 2 papers 22 days ago

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

Paper • 2411.19799 • Published 27 days ago • 10

SeQwen at the Financial Misinformation Detection Challenge Task: Sequential Learning for Claim Verification and Explanation Generation in Financial Domains

Paper • 2412.00549 • Published 25 days ago • 1

DrishtiSharma

authored a paper 24 days ago

1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs

Paper • 2411.06850 • Published Nov 11 • 3

julien-c

posted an update 26 days ago

Post

2193

wow 😮

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

PrimeIntellect/INTELLECT-1-Instruct

jeffboudier

posted an update about 1 month ago

Post

972

New - add your bluesky account to your HF profile:
https://huggingface.co./settings/profile

Is the grass greener, the sky bluer? Will try and figure it out at https://bsky.app/profile/jeffboudier.bsky.social

By the way, HF people starter pack https://bsky.app/starter-pack/huggingface.bsky.social/3laz5x7naiz22

w11wo

authored a paper about 2 months ago

GenUP: Generative User Profilers as In-Context Learners for Next POI Recommender Systems

Paper • 2410.20643 • Published Oct 28

DrishtiSharma

authored a paper 2 months ago

M-RewardBench: Evaluating Reward Models in Multilingual Settings

Paper • 2410.15522 • Published Oct 20 • 11

jeffboudier

posted an update 3 months ago

Post

1072

This week in Inference Endpoints - thx @erikkaum for the update!

👀 https://huggingface.co./blog/erikkaum/endpoints-changelog

1 reply

·

MoritzLaurer

posted an update 3 months ago

Post

4511

#phdone - I defended my PhD yesterday! A key lesson: it is amazing how open science and open source can empower beginners with limited resources:

I first learned about instruction-based classifiers like BERT-NLI 3-4 years ago, through the @HuggingFace ZeroShotClassificationPipeline. Digging deeper into this, it was surprisingly easy to find new datasets, newer base models, and reusable fine-tuning scripts on the HF Hub to create my own zeroshot models - although I didn't know much about fine-tuning at the time.

Thanks to the community effect of the Hub, my models were downloaded hundreds of thousands of times after a few months. Seeing my research being useful for people motivated me to improve and upload newer models. Leaving my contact details in the model cards led to academic cooperation and consulting contracts (and eventually my job at HF).

That's the power of open science & open source: learning, sharing, improving, collaborating.

I mean every word in my thesis acknowledgments (screenshot). I'm very grateful to my supervisors @vanatteveldt @CasAndreu @KasperWelbers for their guidance; to @profAndreaRenda and @CEPS_thinktank for enabling me to work part-time during the first year; to @huggingface for creating awesome tools and an awesome platform; and to many others who are not active on social media.

Links to the full thesis and the collection of my most recent models are below.

PS: If someone happens to speak Latin, let me know if my diploma contains some hidden Illuminati code or something :D

4 replies

·

MoritzLaurer

posted an update 3 months ago

Post

2303

The new NIM Serverless API by HF and Nvidia is a great option if you want a reliable API for open-weight LLMs like Llama-3.1-405B that are too expensive to run on your own hardware.

- It's pay-as-you-go, so it doesn't have rate limits like the standard HF Serverless API and you don't need to commit to hardware like for a dedicated endpoint.
- It works out-of-the box with the new v0.25 release of our huggingface_hub.InferenceClient
- It's specifically tailored to a small collection of popular open-weight models. For a broader selection of open models, we recommend using the standard HF Serverless API.
- Note that you need a token from an Enterprise Hub organization to use it.

Details in this blog post: https://huggingface.co./blog/inference-dgx-cloud
Compatible models in this HF collection: nvidia/nim-serverless-inference-api-66a3c6fcdcb5bbc6e975b508
Release notes with many more features of huggingface_hub==0.25.0: https://github.com/huggingface/huggingface_hub/releases/tag/v0.25.0

Copy-pasteable code in the first comment:

13 replies

·

jeffboudier

posted an update 3 months ago

Post

450

Inference Endpoints got a bunch of cool updates yesterday, this is my top 3

MoritzLaurer

posted an update 3 months ago

Post

1625

Why would you fine-tune a model if you can just prompt an LLM? The new paper "What is the Role of Small Models in the LLM Era: A Survey" provides a nice pro/con overview. My go-to approach combines both:

1. Start testing an idea by prompting an LLM/VLM behind an API. It's fast and easy and I avoid wasting time on tuning a model on a task that might not make it into production anyways.

2. The LLM/VLM then needs to be manually validated. Anyone seriously considering putting AI into production has to do at least some manual validation. Setting up a good validation pipeline with a tool like Argilla is crucial and it can be reused for any future experiments. Note: you can use LLM-as-a-judge to automate some evals, but you always also need to validate the judge!

3. Based on this validation I can then (a) either just continue using the prompted LLM if it is accurate enough and it makes sense financially given my load; or (b) if the LLM is not accurate enough or too expensive to run in the long-run, I reuse the existing validation pipeline to annotate some additional data for fine-tuning a smaller model. This can be sped up by reusing & correcting synthetic data from the LLM (or just pure distillation).

Paper: https://arxiv.org/pdf/2409.06857
Argilla docs: https://docs.argilla.io/latest/
Argilla is also very easy to deploy with Hugging Face Spaces (or locally): https://huggingface.co./new-space?template=argilla%2Fargilla-template-space

jeffboudier

posted an update 3 months ago

Post

4032

Pro Tip - if you're a Firefox user, you can set up Hugging Chat as integrated AI Assistant, with contextual links to summarize or simplify any text - handy!

In this short video I show how to set it up