2). RAG in the Era of Long-Context LLMs – reports that longer-context LLMs suffer from a diminished focus on relevant information, which is one of the primary issues that a RAG system addresses (i.e., uses more relevant information); they propose an order-preserving RAG mechanism
LLMS
-
Strategic Chain-of-Thought Refines LLM Performance by 21%
By
–
3). Strategic Chain-of-Thought – a method to refine LLM performance by incorporating strategic knowledge before the intermediate CoT reasoning steps; the problem-solving strategy helps to guide the generation of the CoT paths and final answers; claims to achieve a 21.05% increase
-
Is MLX suitable for model fine-tuning tasks?
By
–
@awnihannun is this something MLX would be good for fine tuning?
-
MLX Fine-tuning and GGUF Conversion on macOS
By
–
Well thank you both! I’d like to document something for folks to follow along with, so what would you recommend for python and macOS? MLX for fine tuning? And I’ll need gguf iiuc?
-
Fine-tuned Models: Python Implementation for MacOS Users
By
–
Sounds interesting! So what would be the easiest way for me to use a fine-tuned model? BTW since it's in Python, maybe it could be made to work in MacOS too?
-
Which Llama provider features matter most to developers
By
–
Dev community, we'd love your insight! We know there are lots of Llama providers out there, so we're curious: which of these features are the most important to you? #Devs #GenAI
-
Yi-Coder: Sub-10B Coding Model with 125K Context Window Released
By
–
Huge thanks to @josephpollack for bringing this amazing demo! Now Yi-Coder's power is at your fingertips! Joseph Pollack #Ï 🎗️ (@josephpollack) 🙋🏻♂️hey there folks, just released a coding model under 10B parameters with 125K context window , achieving (very high!) SOTA scores on evals. you can try it out for yourself on @huggingface 👇🏻📷 models : huggingface.co/collections/0… @Gradio demo : huggingface.co/spaces/Tonic/… — https://nitter.net/josephpollack/status/1832011077808263388#m
-
Grok AI News App Summarizes X Platform Trends
By
–
I think a big use case is News, leveraging access to content/data/trends on the platform. You could imagine an X news app, which is just Grok summarizing trends on X.
-
Jeremy Howard frustrated by irrelevant replies and hallucinated answers
By
–
Wow an awful lot of replies, but nearly none actually responding to what I'm looking for… C'mon gang if you don't know, that's fine, but don't hallucinate like you're an LLM! This seems to be the one answer that actually fits the request:
-
Project Incorporates PlanSearch Ideas
By
–
Also see this project from @asankhaya
, which now incorporates the core ideas of PlanSearch (one day after the paper!)