Today I just released 0.6.0 which is mainly noticable for having a breaking change: FastHTML's date has been renamed to parsed_date, to avoid clashing with Python's datetime one.
OPEN SOURCE
-
Build Your Own Using Hugging Face Daily Papers API
By
–
build your own using: https://
huggingface.co/api/daily_pape
rs
… -
Dyalog APL Installation Guide Free Download Available
By
–
To use aplnb, you'll need to install Dyalog APL first. It's free (unless you're using it to make money, in which case you gotta buy a license). https://
dyalog.com/download-zone.
htm
… -
APL Magic for Jupyter Notebooks: Quick Calculations Tool
By
–
Something I very frequently want to do is to run a few quick calculations in a notebook — and there's no more powerful way to do quick calculations than @dyalogapl
. Therefore, I've created 'aplnb', which adds a `%%apl` magic to @ProjectJupyter
! -
SMT Solvers and LLMs Automate Euclidean Geometry Formalization
By
–
I agree. We used SMT solvers + LLMs to help auto-formalize Euclidean geometry in Lean. https://
arxiv.org/pdf/2405.17216 -
Claude Sonnet 3.5 Builds HackerNews Daily Papers with Gradio and Replit
By
–
.
@AnthropicAI Sonnet 3.5 built @huggingface daily papers – HackerNews Style @Gradio demo with @Replit agent -
FastHTML GPU.cpp Real-Time Programming Tool Innovation
By
–
This is amaaaazing! This must be the best way to get started with GPU programming now
— Jeremy Howard (@jeremyphoward) 13 septembre 2024
Literally, as you type each char, it creates and runs GPU in real time, runs it, and reports the results.🤯
I didn't expect to see a FastHTML/gpu.cpp cross-over… let alone something so cool. https://t.co/LzVHuDltltThis is amaaaazing! This must be the best way to get started with GPU programming now Literally, as you type each char, it creates and runs GPU in real time, runs it, and reports the results. I didn't expect to see a FastHTML/gpu.cpp cross-over… let alone something so cool.
-
TurboLoRA: Boosting LLM Inference Throughput with Parameter-Efficient Fine-Tuning
By
–
Want to supercharge your #LLM inference? Traditional fine-tuning methods make it possible to achieve #GPT4 level accuracy with small open-source models (#SLMs). But, what about throughput? Introducing #TurboLoRA, a new parameter-efficient fine-tuning method that increases
-
Adapting Meditron Medical AI Model for Cancer Research
By
–
bon bah du coup c'est possible d'1dapter ce qu'ils ont fait avec meditron chez meta pour l'adapter sur mistral ai ? j'ai mon fils de 10 ans qui a un cancer, donc si je peux aider les médecins a faire de la recherche et avoir des réponses les moins biaisées. #medicbrain