Can we use AI to understand how ideas change over time? Stanford scholars use AI tools to measure shifts in public opinion around concepts like immigration, funded by the Hoffman-Yee research grant. https://
bit.ly/45Igylu
MACHINE LEARNING
-
AI measures shifts in public opinion on immigration over time
By
–
-
NeurIPS 2023 ATTRIB Workshop: Understanding ML Model Behavior Attribution
By
–
Recent innovation has given rise to #ML models w/ impressive capabilities, but there’s much to learn about how we attribute model behavior to training data, algorithms, architecture, & more! Have papers or ideas on this? Submit to ATTRIB @ #NeurIPS2023 → http://
attrib-workshop.cc -
Evaluating RAG Pipelines with RAGAS and LangSmith
By
–
Blog: https://
blog.langchain.dev/evaluating-rag
-pipelines-with-ragas-langsmith/
… Webinar: https://
crowdcast.io/c/bnx91nz59cqq Hope to see you there! -
CodeLlama 34B Significantly Improves Coding Performance Over Llama 2
By
–
Llama 2 is awesome, however, coding tasks were not its strong suite. (See HumanEval, a coding-related evaluation task from the paper Evaluating Large Language Models Trained on Code.) The new 34B CodeLlama model is twice as good as the original 70B Llama 2 model and closes the
-
Cotton Ace: AI-Powered Pest Warning System for Farmers
By
–
Cotton Ace is an AI-powered early pest warning and instant advisory system. It helps cotton farmers to protect their crops by providing timely and localized advice on pesticide application, and helps extension workers and administrators to monitor the solution.
-
Groq LPU: AI Hardware Outperforming Graphics Processors
By
–
The Groq Language Processing Unit™ (LPU™) was built for AI from the ground up, enabling Groq to consistently outperform graphics processors on AI and ML tasks. Email contact@groq.com to learn more.
-
Skepticism about few-shot learning effectiveness and token costs
By
–
5-50 examples, I am skeptical that this can even produce good results. Hm, on their website they include a cost example with 100,000 tokens, so this must surely be more than 5-50 examples?
-
QLoRA 4-bit NormalFloat format supported only on Nvidia GPUs
By
–
Ah sorry, I meant M1/M2 chips (not specifically M1/2 CPUs). As far as I know, the 4-bit NormalFloat format that is used in QLoRA is currently only supported on Nvidia GPUs (
https://
github.com/TimDettmers/bi
tsandbytes/issues/485
…). Maybe the repo you mentioned uses a different type of quantized training. -
AI and Machine Learning Accelerate Consumer Deal Psychology Studies
By
–
How AI And Machine Learning Can Help Accelerate Studies Of Consumer Deal Psychology
#AI #AIio #BigData #ML #NLU #Futureofwork @chrismessina @ChristopherIsak @davidwkenny @debashis_dutta @petitegeek @fabiomoioli @GaryMarcus @asokan_telecom http://
ow.ly/shVN30swOv9 -
LoRA Compared to Llama-Adapter and Llama-Adapter v2
By
–
LoRA is a parameter-efficient finetuning technique, yes. I recently compared to Llama-Adapter and Llama-Adapter v2: