In the last couple of days, we talked a lot about extending the context window of transformer LLMs. Here's one more: "Extending Context Window of Large Language Models via Positional Interpolation" 1/3
GENERATIVE AI
-
Open Source LLM App Ideas Community Showcase
By
–
We can't wait to see what you build with it. "Give me some ideas for apps that can be built with an open source LLM."
-
Impressive Open Source LLM Performance with Creative Poetry Generation
By
–
The results are very impressive. You can quickly see why it's the best performing open source LLM. "Write a poem about open source machine learning in the style of Byron."
-
Falcon-40b-instruct Tops OpenLLM Leaderboard Rankings
By
–
Falcon-40b-instruct is the top performing model on the OpenLLM leaderboard. Built by @TIIuae
, it's free to use for commercial and research use. https://
huggingface.co/spaces/Hugging
FaceH4/open_llm_leaderboard
… -
AI Experts Lack Real System Building and Scaling Experience
By
–
Beware of the newly minted #AI experts, they have no clue how to build or scale AI systems! ChatGPT cannot (yet) replace the enterprise software for your business!
-
Appreciation for Different Content Direction from Standard LLM Topics
By
–
Glad to hear that you liked this slight departure from the usual LLM content!
-
ChatGPT speeds up development but complicates debugging
By
–
Before Chatgpt Development : 5 hours
Debugging : 3 hours After Chatgpt Development : 5 min
Debugging : 8 hours I hope u have understood : #chatgpt #ai -
Comprehensive Survey on Large Language Models Evaluation Methods
By
–
A Survey on Evaluation of Large Language Models A comprehensive survey of evaluation methods for LLMs. Focus on “what, where and how to evaluate”. Also shed light on success and failure cases of LLMs in different tasks, and future challenges. Paper: https://
arxiv.org/abs/2307.03109 -
AI Progress: From Skepticism to Practical Implementation Reality
By
–
Amazing how the ai debate has gone from ‘it doesn’t work, it’s a pipe dream’ a decade ago, to ‘great but it’s not 100% accurate all the time so don’t use it for high stakes tasks’… Just give it a couple more years