Vision-Language Pre-training(VLP): Basics, Recent Advances, and Future Trends This is one of the best and comprehensive resources that provides an overview of approaches(basic techniques, model architectures, tasks, benchmarks) used in vision-language pre-training. Just as
@jeande_d
-
LLaMA2 Responsible Usage Guide Released by Meta
By
–
LLaMA2 responsible usage guide(PDF): https://
scontent.fnbo1-1.fna.fbcdn.net/v/t39.8562-6/3
65271716_1020127512503290_6433760642443597145_n.pdf
… Guide website: -
LLaMA2 Guide: Best Practices for LLM Development
By
–
LLaMA2 came with this well-curated guide that includes best practices and resources for working with large language models, LLaMA in particular. This guide is a relevant resource for practitioners and developers(or basically anyone building with LLMs) as it covers important
-
AI Startups Shift from Fancy Landing Pages to Plain HTML
By
–
A paradigm shift in AI new companies these days: fancy landing pages to plain html webpages
-
Appreciation for AI Primers and Guides
By
–
Nice work putting AI primers/guides together, @i_amanchadha
. -
AI Primers and Guides on Diverse Machine Learning Topics
By
–
Really like these primers/guides on nearly any topic you can think of in AI. From model architectures, training techniques, speech, vision, NLP, multimodal, evaluation, etc… https://
aman.ai/primers/ai/ -
AudioCraft: Open-Source Music Generation Model
By
–
Composing music is as nearly hard as drawing/painting a good-looking photo/sketch for most people. We already have open frontier models for generating photo-realistic images but not so many models for music/audio generation.
— Jean de Dieu Nyandwi (@Jeande_d) 3 août 2023
AudioCraft is an open-source tool for generating music… https://t.co/DoNHeg62OrComposing music is as nearly hard as drawing/painting a good-looking photo/sketch for most people. We already have open frontier models for generating photo-realistic images but not so many models for music/audio generation. AudioCraft is an open-source tool for generating music
-
RLHF Limitations and Open Problems in AI Alignment
By
–
RLHF(Reinforcement learning from human feedback) is the common technique used for aligning AI systems(LLMs in particular) with human goals. RLHF works but as with every thing in life, it has flaws too. The paper "Open Problems and Fundamental Limitations of Reinforcement
-
Understanding Transformer Intricacies Through Educational Article
By
–
I wrote the article with people like you in mind. My hope is that the article will help you to understand the intricacies of transformer.
-
OpenAI Cookbook: Essential Resource for API Integration and Tasks
By
–
This Cookbook by OpenAI is an excellent resource that contains code and guides for performing common tasks with OpenAI API, ChatGPT, and their other services. Some examples of guides from the Cookbook: – How to count tokens with tiktoken: https://
github.com/openai/openai-
cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
… – How to