kathir's repositories
Anima
33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU
fineweb-translation
A process to translate fineweb-edu dataset released by huggingface to indian languages using indictrans2 model.
indictrans2-tokenization
A codebase to split text into sentences and tokenize them in batches for inference using IndicTrans2
indictrans2-translation
code to run inference on tokenized sentences using indictrans-2
levanter
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
scalax
A simple library for scaling up JAX programs
autogen
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
corenet
CoreNet: A library for training deep neural networks
deep-learning-with-python-notebooks
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
executorch
On-device AI across mobile, embedded and edge for PyTorch
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
IndicTrans2
Translation models for 22 scheduled languages of India
IndicTransTokenizer
A simple, consistent and extendable module for IndicTrans2 tokenizer
lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
llama-agentic-system
Agentic components of the Llama Stack APIs
llama3
The official Meta Llama 3 GitHub site
maxtext
A simple, performant and scalable Jax LLM!
minbpe
Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
OLMo
Modeling, training, eval, and inference code for OLMo
paxml
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.
system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.