amulil's starred repositories

EasyAnimate

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

Language:PythonLicense:Apache-2.0Stargazers:604Issues:0Issues:0

build-nanogpt

Video+code lecture on building nanoGPT from scratch

Language:PythonStargazers:2508Issues:0Issues:0

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Language:PythonLicense:Apache-2.0Stargazers:17537Issues:0Issues:0

weaviate

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Language:GoLicense:BSD-3-ClauseStargazers:10040Issues:0Issues:0

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

Language:ShellStargazers:5268Issues:0Issues:0

EasyEdit

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Language:Jupyter NotebookLicense:MITStargazers:1548Issues:0Issues:0

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

Language:Jupyter NotebookLicense:MITStargazers:10496Issues:0Issues:0

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

Language:PythonStargazers:441Issues:0Issues:0

llama3.np

llama3.np is a pure NumPy implementation for Llama 3 model.

Language:PythonLicense:MITStargazers:912Issues:0Issues:0

Online-RLHF

A recipe for online RLHF.

Language:PythonStargazers:276Issues:0Issues:0

Llama3-Tutorial

Llama3-Tutorial(XTuner、LMDeploy、OpenCompass)

Language:PythonStargazers:420Issues:0Issues:0

llama3

The official Meta Llama 3 GitHub site

Language:PythonLicense:NOASSERTIONStargazers:22196Issues:0Issues:0

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Language:PythonLicense:Apache-2.0Stargazers:18042Issues:0Issues:0

llm.c

LLM training in simple, raw C/CUDA

Language:CudaLicense:MITStargazers:20899Issues:0Issues:0

HALOs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Language:PythonLicense:Apache-2.0Stargazers:608Issues:0Issues:0

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

Language:PythonLicense:Apache-2.0Stargazers:1090Issues:0Issues:0

optimum-quanto

A pytorch quantization backend for optimum

Language:PythonLicense:Apache-2.0Stargazers:627Issues:0Issues:0

argilla

Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.

Language:PythonLicense:Apache-2.0Stargazers:3221Issues:0Issues:0

min-max-gpt

Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training

Language:PythonStargazers:97Issues:0Issues:0

gradient-checkpointing

Make huge neural nets fit in memory

Language:PythonLicense:MITStargazers:2646Issues:0Issues:0

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

Language:PythonLicense:NOASSERTIONStargazers:2497Issues:0Issues:0

Awesome-LLMs-Datasets

Summarize existing representative LLMs text datasets.

License:Apache-2.0Stargazers:651Issues:0Issues:0

Megatron-LM

Ongoing research training transformer models at scale

Language:PythonLicense:NOASSERTIONStargazers:9122Issues:0Issues:0

Warp

Warp is a modern, Rust-based terminal with AI built in so you and your team can build great software, faster.

License:NOASSERTIONStargazers:20024Issues:0Issues:0

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Language:PythonLicense:MITStargazers:8574Issues:0Issues:0

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Language:PythonLicense:Apache-2.0Stargazers:390Issues:0Issues:0

SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)

Language:PythonLicense:Apache-2.0Stargazers:867Issues:0Issues:0

axolotl

Go ahead and axolotl questions

Language:PythonLicense:Apache-2.0Stargazers:6626Issues:0Issues:0

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Language:PythonLicense:MITStargazers:5674Issues:0Issues:0

alignment-handbook

Robust recipes to align language models with human and AI preferences

Language:PythonLicense:Apache-2.0Stargazers:4111Issues:0Issues:0