more project everyday using the daily papers api: https://
github.com/l-yohai/daily_
papers_ko
…, some nice use cases, its free to use
OPEN SOURCE
-
Daily Papers API: Free Project Showcase with Nice Use Cases
By
–
-
Exploring Hugging Face Papers API and Community Projects
By
–
nice also check out https://
huggingface.co/papers and several projects built with the api like https://
github.com/gabrielchua/da
ily-ai-papers
… might be helpful docs on the api here: https://
huggingface.co/docs/hub/en/ap
i#get-apiarxivarxividrepos
…, if you want to build your own app -
Google Demos PaliGemma Open Vision-Language Model at ECCV2024
By
–
At #ECCV2024? Join us at the Google Booth where Google researcher @AndreasPSteiner will demo PaliGemma, a versatile open 3B vision-language model, which can easily be fine-tuned and runs on small accelerators, or even on a modern CPU.
-
Google Releases Gemma-2-JPN Japanese Language Model
By
–
GoogleからGemma-2-JPNがリリースされました！このモデルはGemma 2 2Bを日本語でfine-tuneしたものです。Gemma 2の英語での性能と同レベルの性能で日本語をサポートします。
モデル一覧: -
Daily Research Bot: AI Discord Bot for Translation Research
By
–
Daily Research Bot an AI-powered Discord bot that helps you stay on top of new AI-related research, with a focus on low-resource language translation tasks. It summarizes recent papers from sources like Hugging Face and Elvis Saravia's blog, providing concise insights and
-
Optimizing AI Models with torch.compile and FSDP2
By
–
we spend a lot of time optimizing decently-sized models too.
For anything that is normal-sized (one node, 8 GPUs), torch.compile + FSDP2 should be largely sufficient to get to really good performance.
We've spent hundreds (or probably thousands) of programmer-years working on -
Handling Large Text Inputs with Longformer Transformers
By
–
How to Handle Large Text Inputs with Longformer and Hugging Face Transformers: Let’s learn how to handle large text inputs in the Large Language Model (LLM). Preparation Ensure you have the Transformers and datasets package from Hugging Face… https://
kdnuggets.com/how-to-handle-
large-text-inputs-with-longformer-and-hugging-face-transformers?utm_source=dlvr.it&utm_medium=twitter
… -
Interoperability Path for Open Table Formats Explored
By
–
Explore the path to interoperability with @michaelarmbrust (the original creator of #DeltaLake) & Ryan Blue (an original creator of #ApacheIceberg). They discuss the evolution of open table formats, how Databricks is solving interoperability & more: https://
dbricks.co/4ejg3my -
Targeting checkpointing improvements planned for machine learning
By
–
it's on our list of things to do (more targeting checkpointing, not FSDP). I wrote up a plan / doc early last year about it.
-
Llama 3.2 Launches with Record-Breaking Inference Speed Performance
By
–
Llama 3.2 is here and we're faster than ever! We've been independently verified as the fastest #AI #Inference on @AIatMeta
's Llama 3.2 1B & 3B with … 2470 tokens/sec on 1B 1566 tokens/sec on 3B … all running at full-precision! Start developing