OpenBMB/ToolBench: An open platform for training, serving, and evaluating large language model for tool learning. https://
bit.ly/3s0agPn
LLMS
-
ToolBench: Open Platform for LLM Tool Learning
By
–
-
LLM Prompt Variants for Business Idea Validation
By
–
Added some variants that work for other models Llama: https://
smith.langchain.com/hub/hwchase17/
matt-shumer-validate-business-idea-llama
… Google Palm: https://
smith.langchain.com/hub/hwchase17/
matt-shumer-validate-business-idea-google-palm
… -
Faith and Fate: Transformer Compositionality Limits Study
By
–
Faith and Fate: Limits of Transformers on Compositionality Dziri et al.: https://
arxiv.org/abs/2305.18654 #Artificialintelligence #DeepLearning #Transformers -
Tokenizer vocabulary size comparison across language models
By
–
Sunday small guessing puzzle Let's say I have 3 tokenizers:
– llama2: 32k vocab
– falcon: 65k vocab
– GPT4: 100k vocab I take ~2M random documents from the web (let’s say 10 random parquet files from RefinedWeb from https://
huggingface.co/datasets/tiiua
e/falcon-refinedweb
… roughly 1B tokens). I tokenize them -
ChatGPT generates 87.5% of top ideas in student research study
By
–
“we investigated only the subset of the best ideas in our pool—specifically the top 10%. Of these 40 ideas, five were generated by students and 35 were created by ChatGPT” https://
apple.news/Aza2b5PjfTpyTU
7tNjgGZNQ
… -
Transformers Can Learn Hierarchical Structures Through Parse Trees
By
–
Why do you say we haven’t solved “hierarchical structure”? Transformers can learn parse trees & bracketing, each of which is full generalizable to arbitrary hierarchies. I think we totally machine learn hierarchical structures now.
-
Researchers Discovered ChatGPT Vulnerabilities and Future AI Implications
By
–
How researchers broke ChatGPT and what it could mean for future AI development https://
zd.net/3YrH7J1 #AI #MachineLearning #DeepLearning #LLMs #DataScience -
LLMs Water Consumption Crisis: Urgent Call for Industry Action
By
–
For all the companies promising “watermarks” for AI – eventually, in ways nobody believes will slow down LLM adoption – my appeal is for them to leave their “mark on water” and encourage no LLMs are used until they stop radically & rapidly using water NOW. Be heroes. #LLMsNoH20
-
Satya Nadella’s Intelligence Is Not Artificial
By
–
Satya Nadella’s Intelligence Is Not Artificial – Freakonomics https://
bit.ly/3QvoIcG #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Large Language Models as Optimizers: Yang et al Research
By
–
Large Language Models as Optimizers Yang et al.: https://
arxiv.org/abs/2309.03409 #ArtificialIntelligence #DeepLearning #LargeLanguageModels