-
ModelCloud.ai
- Earth/Epoch 2.0
- https://modelcloud.ai
- @qubitium
-
sglang Public
Forked from sgl-project/sglangSGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
-
unsloth Public
Forked from unslothai/unsloth5X faster 60% less memory QLoRA finetuning
Python Apache License 2.0 UpdatedAug 30, 2024 -
vllm Public
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Python Apache License 2.0 UpdatedAug 1, 2024 -
BitBLAS Public
Forked from microsoft/BitBLASBitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
Python MIT License UpdatedJul 23, 2024 -
auto-round Public
Forked from intel/auto-roundSOTA Weight-only Quantization Algorithm for LLMs
Python Apache License 2.0 UpdatedJul 23, 2024 -
hqq Public
Forked from mobiusml/hqqOfficial implementation of Half-Quadratic Quantization (HQQ)
Python Apache License 2.0 UpdatedJul 22, 2024 -
AutoGPTQ Public
Forked from AutoGPTQ/AutoGPTQAn easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
-
accelerate Public
Forked from huggingface/accelerate🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Python Apache License 2.0 UpdatedJun 21, 2024 -
qlora Public
Forked from artidoro/qloraQLoRA: Efficient Finetuning of Quantized LLMs
Jupyter Notebook MIT License UpdatedJun 15, 2024 -
flashinfer Public
Forked from flashinfer-ai/flashinferFlashInfer: Kernel Library for LLM Serving
Cuda Apache License 2.0 UpdatedJun 15, 2024 -
transformers Public
Forked from huggingface/transformers🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python Apache License 2.0 UpdatedJun 5, 2024 -
AutoAWQ Public
Forked from casper-hansen/AutoAWQAutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
Python MIT License UpdatedMar 25, 2024 -
lm-format-enforcer Public
Forked from noamgat/lm-format-enforcerEnforce the output format (JSON Schema, Regex etc) of a language model
Python MIT License UpdatedMar 18, 2024 -
gemma_pytorch Public
Forked from google/gemma_pytorchThe official PyTorch implementation of Google's Gemma models
Python Apache License 2.0 UpdatedMar 12, 2024 -
flash-attention Public
Forked from Dao-AILab/flash-attentionFast and memory-efficient exact attention
Python BSD 3-Clause "New" or "Revised" License UpdatedFeb 18, 2024 -
alpaca-lora Public
Forked from tloen/alpaca-loraInstruct-tune LLaMA on consumer hardware
Jupyter Notebook Apache License 2.0 UpdatedMay 27, 2023 -
GPTQ-triton Public
Forked from fpgaminer/GPTQ-tritonGPTQ inference Triton kernel
Jupyter Notebook Apache License 2.0 UpdatedMay 24, 2023 -
GPTQ-for-LLaMa Public
Forked from qwopqwop200/GPTQ-for-LLaMa4 bits quantization of LLaMa using GPTQ
Python Apache License 2.0 UpdatedMay 19, 2023 -
llama.cpp Public
Forked from ggerganov/llama.cppPort of Facebook's LLaMA model in C/C++
C MIT License UpdatedMay 3, 2023 -
hyperDB Public
Forked from jdagdelen/hyperDBA hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $35M cap.
Python MIT License UpdatedApr 20, 2023 -
FastChat Public
Forked from lm-sys/FastChatThe release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
Python Apache License 2.0 UpdatedApr 9, 2023 -
GPT-4-LLM Public
Forked from Instruction-Tuning-with-GPT-4/GPT-4-LLMApache License 2.0 UpdatedApr 7, 2023 -
the-algorithm Public
Forked from twitter/the-algorithmSource code for Twitter's Recommendation Algorithm
Scala GNU Affero General Public License v3.0 UpdatedMar 31, 2023 -
gpt4all Public
Forked from nomic-ai/gpt4allgpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue
Python UpdatedMar 31, 2023 -
llama-dl Public
Forked from Elyah2035/llama-dlShell GNU General Public License v3.0 UpdatedMar 21, 2023 -
TTS Public
Forked from coqui-ai/TTS🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Python Mozilla Public License 2.0 UpdatedOct 15, 2022 -
ZeroTierOne Public
Forked from zerotier/ZeroTierOneA Smart Ethernet Switch for Earth
C++ Other UpdatedJun 28, 2022 -
C4_200M-synthetic-dataset-for-grammatical-error-correction Public
Forked from google-research-datasets/C4_200M-synthetic-dataset-for-grammatical-error-correctionThis dataset contains synthetic training data for grammatical error correction. The corpus is generated by corrupting clean sentences from C4 using a tagged corruption model. The approach and the d…
Python Creative Commons Attribution 4.0 International UpdatedDec 7, 2021 -
-
libheif Public
Forked from strukturag/libheiflibheif is an HEIF and AVIF file format decoder and encoder.
C++ Other UpdatedJul 13, 2020