Large language models (LLMs) are trained on human-generated text, but additional methods are needed to align an LLM with human values and preferences. To align models with human values and individual RLHF is a highly recommended solution
LLMS
-
Beyond Language: Why GPT-4 Needs Training Data
By
–
long story short, my task can't be completed by GPT-4; the data isn't only language, it includes continuous vectors, so you really need training data for this
-
Fine-tuning LLM into Specialized Financial Expert
By
–
Good morning fellow AI enthusiast! This is the last video in our series on training and fine-tuning your LLM built for the course with @towards_AI and @activeloop
! We are transforming a generalist LLM into a specialized financial expert! https://
open.substack.com/pub/louisbouch
ard/p/how-to-fine-tune-your-llm-on-tweets?r=25qlky&utm_campaign=post&utm_medium=web&showWelcome=true
… -
AI Waifus: Low Latency Response Technology Future
By
–
When we get this to latency answering of <5ms it will be an instant unicorn. AI Waifus instead of real wives: insta win
-
Handwriting to Text GPT converts note images to digital text
By
–
You can't keep track of all your handwritten notes.
— God of Prompt (@godofprompt) 16 décembre 2023
That's why I made Handwriting to Text GPT.
Simply upload any image of your notes/sketches/documents and it will transcribe them for you in seconds!
Try it out here: https://t.co/1CIaWAQcgi#handwriting #Text #customgpts… pic.twitter.com/g2lELOeqFYYou can't keep track of all your handwritten notes. That's why I made Handwriting to Text GPT. Simply upload any image of your notes/sketches/documents and it will transcribe them for you in seconds! Try it out here: https://
godofprompt.ai/gpts/handwriti
ng-to-text-gpt
… #handwriting #Text #customgpts -
Reinforcement Learning for Diffusion Models from Scratch
By
–
Dr. Tanishq Abraham – Reinforcement Learning for Diffusion Models from Scratch https://
bit.ly/3GuPUBM #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Real Life Usecase Comparison: Claude2 vs ChatGPT
By
–
Compared to claude2 and ChatGPT: what has the most real life usecase?
-
Google Gemini Pro Shows Significant Improvements in Understanding and Reasoning
By
–
Internal performance evaluations from Google have shown significant improvements for Gemini Pro over previous Google models in understanding, summarization, reasoning, coding, and planning. This model also excels in cross-modal reasoning. (2/3)
-
Open-source LLMs guide with interactive examples
By
–
Our second Replicate guide is live – it's a good one:
— fofr (@fofrAI) 15 décembre 2023
A guide to open-source LLMshttps://t.co/dQXR17bfVk
Special appearance by @WTTDFP 🙌
I love the interactive examples pic.twitter.com/UFlx1gKskiOur second Replicate guide is live – it's a good one: A guide to open-source LLMs https://
replicate.com/guides/languag
e-models
… Special appearance by @WTTDFP I love the interactive examples -
Chat Completions endpoint now supports logprobs feature
By
–
Just wanted to drop some good news in this thread: we’ve now added logprobs to the Chat Completions endpoint. Thank you for your precious feedback!