Fabrizio Milo's repositories
autocrit
A repository for transformer critique learning and generation
axolotl
Go ahead and axolotl questions
candle
Minimalist ML framework for Rust
clip-interrogator
Exctract CLIP info from image
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
dspy
DSPy: The framework for programming—not prompting—foundation models
guidance
A guidance language for controlling large language models.
instructor
structured outputs for llms
langchain
⚡ Building applications with LLMs through composability ⚡
llama
Inference code for genesis models
llama.cpp
Port of Facebook's LLaMA model in C/C++
LLMCompiler
LLMCompiler: An LLM Compiler for Parallel Function Calling
lm-evaluation-harness
A framework for few-shot evaluation of language models.
LocalAI
:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs ggml, gguf, GPTQ, onnx, TF compatible models: llama, llama2, rwkv, whisper, vicuna, koala, cerebras, falcon, dolly, starcoder, and many others
metaflow
:rocket: Build and manage real-life data science projects with ease!
mlx
MLX: An array framework for Apple silicon
mlx-examples
Examples in the MLX framework
mlx-moe
Scripts to create your own moe models using mlx
ollama
Get up and running with large language models locally
OLMo
Modeling, training, eval, and inference code for OLMo
pytorch-custom-utils
Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new AI research
self-rewarding-lm-pytorch
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
stable-diffusion
A latent text-to-image diffusion model
synthetic-data-blog
This is the reproduction repository for my 🤗 Hugging Face blog post on synthetic data
torchtitan
A native PyTorch Library for large model training
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)