Embedding Explorer
AI
Introduction - Hugging Face NLP Course
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Debugging Llama 3.1-8B with Dr. Droid
A guide to fine-tuning the Llama 3.1-8B model and using Doctor Droid Playbooks for faster debugging
Notes by Doctor Droid
Doctor Droid team shares product guides, demos and best practices in observability.
mlabonne/llm-course: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks. - mlabonne/llm-course
2409.01374
hiyouga/LLaMA-Factory: Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024) - hiyouga/LLaMA-Factory
Fine-Tuning Llama 3 on TIR
This tutorial offers a step-by-step guide to fine-tune Llama 3 on E2E Networks’s TIR platform for answering finance-related queries.
mlabonne/orpo-dpo-mix-40k · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
LiveBench
Introducing Triton: Open-source GPU programming for neural networks | OpenAI
We’re releasing Triton 1.0, an open-source Python-like programming language which enables researchers with no CUDA experience to write highly efficient GPU code—most of the time on par with what an expert would be able to produce.
unslothai/unsloth: Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory - unslothai/unsloth
Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth
A Blog post by Maxime Labonne on Hugging Face
SFT
SEAL LLM Leaderboards: Expert-Driven Private Evaluations
Explore the SEAL leaderboards for expert-driven, private, regularly updated LLM rankings and evaluations across domains like coding, instruction following and more!
Accelerate the Development of AI Applications | Scale AI
Trusted by world class companies, Scale delivers high quality training data for AI applications such as self-driving cars, mapping, AR/VR, robotics, and more.
Lets verify step by step
Where LLM Fails: Easy Problems That LLMs Get Wrong
Understanding LLM Hallucinations and how to mitigate them
Explore the phenomenon of Large Language Model (LLM) hallucination in-depth, discovering real-world examples, causes, and mitigation strategies. Understand the potential adverse outcomes in fact-driven fields like law, healthcare, and finance.
4 LLM Hallucination Examples and How to Reduce Them
What is LLM hallucination & the four most common hallucination types and the causes for them
Forced
Top LLM strengths and weaknesses | Retool Blog | Cache
Large language models (LLMs) have strengths and weaknesses like any emerging technology. Read which use cases help you get the most out of your LLMs.
The no-code AI platform for text - Lettria
Structuring textual data easy, collaborative, and efficient. Turn Lettria’s platform into a customized NLP and start harnessing the true power of your data.
Vector Database vs. Graph Database: Lessons Learned from Marvel | Tars Blog
This blog has been adapted from our weekly newsletter. For more updates click here. Vector databases have become a hot topic in the tech world. The appeal lies in their ability to quickly find similar information in unstructured data. However, just like you ignored the red flags in your high school crush, this hype overlooks its […]
Detect-AI-text-Easily/ai_words.txt at main · FareedKhan-dev/Detect-AI-text-Easily
Some words that LLM regularly uses.
AI or Human: Can you tell the difference?
Play the game and try to guess the difference between what is AI or Human.
Glaive - Language models for all
Build and improve custom datasets for your use case.
Microsoft’s GraphRAG + AutoGen + Ollama + Chainlit = Fully Local & Free Multi-Agent RAG Superbot
This superbot app integrates GraphRAG with AutoGen agents, powered by local LLMs from Ollama, for free & offline embedding & inference.
Prompt Engineering Is Dead: DSPy Is New Paradigm For Prompting
DSPy Paradigm: Let’s program — not prompt — LLMs
Extracting Meaning from Tables in Financial Statements With LLMs and Chatbots (Using Unstructured.io
Hello guys, welcome back to another exciting project. Chatting with textual data using LLMs and chatbots has become easy and…
Why RAG Applications Fail in Production
It worked as a prototype; then all went down!
Exciting New Methods for Efficient Fine-Tuning of LLMs using PEFT (BOFT, VeRA, and PiSSA)
The latest update to Huggingface’s PEFT v0.11.0 introduces several new Parameter-Efficient Fine-Tuning (PEFT) techniques (BOFT, VeRA, and…