Alberto Ferrer's repositories
transmla-converter
TransMLA: Multi-Head Latent Attention Converter
ai-algorithms
First-principle implementations of groundbreaking AI algorithms using a wide range of deep learning frameworks, accompanied by supporting research papers.
AutoDidact
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
blurred-thoughts-SFT
Blurred-Thoughts Supervised-Finetuning (BT-SFT) is a new approach to fine-tuning language models, focusing on enhancing response diversity and creativity.
CAG
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
chain-of-draft
Code and data for the Chain-of-Draft (CoD) paper
chonkie
🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library
docling-serve
Running Docling as an API service
FastGPT
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
guardrails
Adding guardrails to large language models.
haystack-rag-app
An example of a RAG backend plus UI
khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
LightRAG
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
LLaDA
Official PyTorch implementation for "Large Language Diffusion Models"
MCP-Bridge
A middleware to provide an openAI compatible endpoint that can call MCP tools
mistral.rs
Blazingly fast LLM inference.
nanoRLHF
RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.
open-r1-multimodal
A fork to add multimodal model training to open-r1
open-webui-mcp
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
openwebui-migrator
Open WebUI Database Migrator
OpenWebUI-Tools
Tools for OpenWebUI
R1-V
Witness the aha moment of VLM with less than $3.
R2R
The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.
R2R-Application
react + next.js dashboard for R2R: The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.
SoT
Official code repository for Sketch-of-Thought (SoT)
unsloth-docker
Unsloth Training Environment
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs