Natural Language Processing
102 Threads
Another 'WOW' paper - Upto 20x improvement in inference throughput with Block Transformer compared to vanilla transformers with equivalent perplexity.🤯 How ❓ by MASSIVELY reducing...
1/n An ontology for hallucination mitigation techniques in Large Language Models (LLMs). Prompt Engineering category A. Retrieval Augmented Generation (RAG) - Before Generati...
We've seen that smaller chunks are good for capturing semantic meaning and larger ones are good for providing better context. @llama_index AutoMergingRetriever takes it one step f...
Does a language model trained on “A is B” generalize to “B is A”? E.g. When trained only on “George Washington was the first US president”, can models automatically answer “Who was...
Most people haven’t really changed the way they prompt ChatGPT in months. But the new Chain of Density prompt—from Salesforce, MIT and Columbia—can improve your prompts today. It...
Previously we've seen @LangChainAI ParentDocumentRetriever that creates smaller chunks from a document and links them back to the initial documents during retrieval. MultiVectorRe...
ChatGPT’s limitations make it nearly useless. When compared to tools like LangChain. Unfortunately, most people haven't even heard of LangChain. • Fine tune on PDFs • Search the...
I just added @nomic_ai new GPT4All Embeddings to @LangChainAI. Here's a new doc on running local / private retrieval QA (e.g., on your laptop) w/ GPT4All embeddings + @trychroma +...
LLMs have taken the world by storm, and attention is everywhere! It's about time we understand how things work! Today, I'll clearly explain the self-attention mechanism! Let's g...
ChatGPT has now a serious competitor. Anthropic has just released Claude 2 and it's really powerful. Here's why you should use Claude 2 instead of ChatGPT (for free): [Thread] h...
LLM's are great, but slow in production. Meet vLLM, an open-source library that accelerates HuggingFace Transformers by a mind-blowing 24x!. Let's dive into what this means for l...
Article 4 of 5: Transformers in Practice: BERT, GPT, and Others Introduction In the world of natural language processing (NLP), Transformer models have revolutionized the way we...
Article 2 of 5: Deep Dive into the Attention Mechanism Introduction The attention mechanism is a pivotal concept in the architecture of Transformer models, which have revolutioni...
Article 1 of 5: Introduction to Transformers in AI Introduction In the realm of Artificial Intelligence (AI), particularly in the field of Natural Language Processing (NLP), the...
"The Complete Bozos Guide to Fine-tuning" • What is Fine-tuning? • How to Fine-tune a custom LLM. • When should we use fine-tuning? • When NOT use use fine-tuning? Save This ↓ ht...
🚀📢 GPT models have blown our minds with their astonishing capabilities. But, do they truly acquire the ability to perform reasoning tasks that humans find easy to execute? NO⛔️ We...
The problem with ChatGPT is that it writes like a robot. But you can train it to write exactly like you. Here's how you can easily train ChatGPT with only one prompt:
4-bit QLoRA is here to equalize the playing field for LLM exploration. You can now fine-tune a state-of-the-art 65B chatbot on one GPU in 24h. Paper: https://t.co/7gX1oIUHEx Code...
🧵 Ever wanted to talk with your LLM🤖 on some custom data that it wasn't originally trained on? @LangChainAI 🦜🔗+ @pinecone 🌲vectorstore will do all the heavy lifting for you. Here'...
There are currently 4,278 AI tools available. As an academic I use only 5 regularly for my research. Here's why I use them and their tutorials: 👇 https://t.co/YeaG6HCtiW
All you need to know about LLMs: • Overview • Using LLMs in @LangChainAI • Using open-sourced LLMs • Chat Model • How do we embed text? Save this ↓ https://t.co/JebchVN9gz
The last few days in AI development is insane. Google X Adobe ChatGPT new UI Midjourney 3d model ChatGPT Plugins release Coca-Cola new Ad with AI Google new Universal Translator A...
ChatGPT has serious competition. Bard is here. Bard can do some CRAZY things that ChatGPT cannot. Don’t believe me? Here’s proof: https://t.co/jUY2uqHR84
LLMs are revolutionizing the AI world, and attention is everywhere! Today, I'll clearly explain how self-attention works! 🚀 A Thread 🧵👇 https://t.co/wkMtGD0pDJ