Size of the code must be included in overall LM size computation
LLMS
-
LangChain Tool Calling Enables Cross-Model Agent Development
By
–
"LangChain Tool Calling feature just changed everything" We recently added a common interface for tool calling across model providers This makes it easy to build agents that work across models Watch @EdenEmarco177 explain why this is a big deal https://
youtube.com/watch?v=dj8Yqi
E1Omc
… -
Daily Content on Python, Data Science, Machine Learning, and MLOps
By
–
That's a wrap! If you are interested in any of these below topics: – Python – Data Science – Machine Learning – Data Analysis – LLMs – MLOps Find me → @Sumanth_077 I'm sharing daily content over here.
-
Improving LLM Performance Through Chain of Thought Reasoning
By
–
One of the best ways to improve LLM performance is to ask it to “think aloud” (there are various techniques for doing this, including Chain of Thought). This also helps establish clearly the AIs plans. This paper suggests that, in some cases, the AI can plan without revealing it
-
LLMs Copyright Violation: The Sin of Synthetic AI
By
–
Being in the moment means seeing yourself or someone else. It’s a core proof you’re alive. Love galvanizes these moments. Romantic, parental, friendship – a moment of kindness. LLMs violating copyright law means stealing people’s human moments, w/o love, hence: Sin-Thetic AI.
-
Parameter-Efficient Fine-Tuning Methods for Large Language Models
By
–
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey PEFT algorithms are useful for dealing with LLMs with high parameter counts, as even fine-tuning these models from scratch can be computationally expensive and resource-intensive. https://
arxiv.org/abs/2403.14608 -
Llama3-405B: Open Source Models Cost Advantage
By
–
I’m bullish on OSS models like Llama3-405B. 70B is just as good as Claude Sonnet, but already an order of magnitude cheaper. The cost equation goes down quite a bit if it’s not through a closed model provider. Reliability will need technical ingenuity.
-
LLMs errors tolerance: rethinking AI deployment beyond zero-error
By
–
I think too many people think only of AI use in places where errors are not tolerated. It isn't good at that. LLMs hallucinate & make mistakes. But for a huge amount of work, human error is tolerated, and the question is whether AIs (working with humans) make more or less
-
Managing GPT-4 Effectively: Guidance and Instructions Matter
By
–
In the executive MBA class I taught today, a student said something very useful to understand about AI: They said you have to approach working with GPT-4 as a manager, and if doesn't do something right, you need to provide more direction, rules, or instructions. That often helps
-
Large Context Windows Boost LLM Performance Through Many-Shot Learning
By
–
Very large context windows may extend the capabilities of LLMs because you can give them hundreds of examples on how to solve a problem (many shot learning). This paper from Google finds significant performance boosts from many shot, even when the AI generates its own examples.