Mastering #NLProc from Foundations to #LLMs — Apply Advanced NLP Techniques to Solve Real World Business Problems: https://
amzn.to/3TawZDK (
@PacktPublishing release May 9. Pre-order now for price guarantee)
———
#DataScience #GenerativeAI #AI #MachineLearning #DeepLearning #GenAI
LLMS
-
Mastering NLP: From Foundations to Large Language Models
By
–
-
Smart AI System Demonstrates Intelligence and Refined Taste
By
–
Not only is it smart, but it also has taste!
-
Was Claude’s AI Protagonist Named After Prometheus Code
By
–
This is actually super interesting because last night I was co-writing a short story with Claude and insisted on calling the protagonist, a sentient AI, Prometheus. I wonder if that was its code name.
-
Microsoft Google Apple AI execution and answer engines
By
–
Who is executing well, and who is executing poorly, between Microsoft & Google? What do you think of Apple in AI? Is "answer engine" a similar change to the kind Google's Pagerank brought to web portals 20 years ago? What does it mean to search like Jensen Huang? These are some
-
Claude 3 Outperforms GPT-4 in User Experience
By
–
Interesting results! For me, Claude 3 is so much better than GPT-4, to the point where I stopped using GPT
-
New Extraction Guides for Structured Data from Unstructured Text
By
–
New extraction guides Reliably extracting structured data from unstructured text is one of the killer use-cases for LLMs. It's a fantastic way to bridge the gap between LLMs and traditional APIs and systems. We've put a lot of work on this lately, including an open
-
Fine-tuning LLMs: Democratizing AI Performance with Smaugh
By
–
Fine-tuning can change and customize your LLMs to your particular domain, allowing even the GPU poor to improve base models by 10-15%. Additionally, it’s the way for open-source AI to match GPT-4 performance. In the past month, we at Abacus AI have been announcing Smaugh
-
Testing Megaprompts on Claude-3 and Gemini Ultra Models
By
–
Whenever a new foundational model comes I like to run my best megaprompts in it. Gemini Ultra has been awesome at this. So is Claude-3. But Claude-3 has a huge context window. Praying Gemini Ultra will get one soon. I need those tokens!
-
Yi-34B-200K Achieves 99.8% Performance in Long Context Test
By
–
Yi-34B-200Khas enhanced the long text capability. In the Needle-in-a-Haystack test, the performance rises from 89.3% to 99.8%. @01AI_Yi continues to pretrain the model on 5B tokens long-context data mixture and demonstrates a near-all-green performance!
https://
github.com/01-ai/Yi?tab=r
eadme-ov-file#news
… -
Data formatting example for Mistral fine-tuning
By
–
And if you are curious, this is what my data looks like. It was formatted for fine-tuning Mistral, which is why you see the [INST][/INST] and .