rasbt / LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
☆38,476Updated this week
Alternatives and similar repositories for LLMs-from-scratch:
Users that are interested in LLMs-from-scratch are comparing it to the libraries listed below
- Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory☆21,119Updated this week
- Machine Learning Engineering Open Book☆12,503Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆11,257Updated this week
- Awesome-LLM: a curated list of Large Language Model☆20,933Updated last week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆38,723Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆34,628Updated this week
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆16,019Updated this week
- Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work t…☆25,314Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,052Updated this week
- The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more.☆30,740Updated this week
- Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.☆44,219Updated this week
- llama3 implementation one matrix multiplication at a time☆14,061Updated 8 months ago
- Convert PDF to markdown + JSON quickly with high accuracy☆19,517Updated this week
- LLM inference in C/C++☆71,220Updated this week
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆21,854Updated this week
- Build multi-modal Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.☆18,184Updated this week
- SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensiv…☆14,269Updated this week
- OCR, layout analysis, reading order, table recognition in 90+ languages☆15,644Updated this week
- A Gradio web UI for Large Language Models with support for multiple inference backends.☆41,769Updated this week
- LlamaIndex is the leading framework for building LLM-powered agents over your data.☆38,276Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆38,694Updated last month
- The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.☆15,491Updated last month
- Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sag…☆16,565Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆9,338Updated 6 months ago
- Automate browser-based workflows with LLMs and Computer Vision☆11,737Updated this week
- Go ahead and axolotl questions☆8,376Updated this week
- DSPy: The framework for programming—not prompting—language models☆21,321Updated this week
- 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.☆12,766Updated 2 months ago
- Building a quick conversation-based search demo with Lepton AI.☆7,952Updated last week
- Fast and memory-efficient exact attention☆15,164Updated last week