#LLMs are revolutionizing code generation, but ensuring accuracy with domain-specific tools like Spark SQL is vital. Discover how to synthesize tailored code tests for LLMs, offering a precise way to evaluate performance across any coding library.
RESEARCH
-
DDP versus FSDP2 model training strategy selection
By
–
DDP or FSDP2, depending on the type of model. If it can saturate compute with DDP, then that's simpler and already good. If not, FSDP2.
-
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 -
Async Re-explored in AI Industry Research
By
–
yes, async is actively being re-explored in the industry.
Arthur / M'aurelio have been publishing on it, so are some other folks. -
Blavatnik Awards Honor for AI and Science Research
By
–
An amazing night at @AMNH for the @BlavatnikAwards dinner gala. Thank you for the honor! It really goes to my team at @Caltech and my collaborators working on the frontier of AI+Science.
-
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
… -
LLMs Generate More Novel Research Ideas Than Humans
By
–
Can LLMs Generate Novel Research Ideas? This paper from @StanfordAILab performs a human study with 100+ NLP researchers and discovers that LLM-generated ideas are more novel! Excited to have the authors @ChengleiSi @Diyi_Yang and @tatsu_hashimoto here to discuss their work!
-
AI Applications and Risks in Pharmaceutical Drug Research Development
By
–
Discover the potential and risks of AI in drug R&D with insights from Mirit Eldor, MD, Elsevier’s Life Sciences Solutions, at BioTechX EU 2024. Learn more – https://
terrapinn.com/conference/bio
techx/index.stm
… #BioTechX #data #AI #IoT #Pharma -
Foundation Models Master Zero-Shot Learning in Chaotic Systems
By
–
Zero-shot forecasting of chaotic systems https://
bit.ly/3XMvnBe
New foundation models are showing promise for zero-shot learning in chaotic systems that reveals they can compete with custom models, capturing long-term behaviors #AI #MachineLearning #DeepLearning #LLMs -
New Robot Imitation Learning Approach Presentation at CORL
By
–
Looking fwd to Justin and Chung-Min presenting this exciting new approach to robot imitation learning @corl_conf https://t.co/Y4D0OwhCBM
— Ken Goldberg (@Ken_Goldberg) 2 octobre 2024Looking fwd to Justin and Chung-Min presenting this exciting new approach to robot imitation learning @corl_conf