tugstugi's Stars
myshell-ai/OpenVoice
Instant voice cloning by MyShell.
hiyouga/LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
unslothai/unsloth
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
VikParuchuri/surya
OCR, layout analysis, reading order, line detection in 90+ languages
Plachtaa/VALL-E-X
An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io
jasonppy/VoiceCraft
Zero-Shot Speech Editing and Text-to-Speech in the Wild
Vaibhavs10/insanely-fast-whisper
OpenAccess-AI-Collective/axolotl
Go ahead and axolotl questions
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
Beomi/KoAlpaca
KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델
AnswerDotAI/fsdp_qlora
Training LLMs with QLoRA + FSDP
abacaj/fine-tune-mistral
Fine-tune mistral-7B on 3090s, a100s, h100s
arielnlee/Platypus
Code for fine-tuning Platypus fam LLMs using LoRA
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
longyuewangdcu/Chinese-Llama-2
improve Llama-2's proficiency in comprehension, generation, and translation of Chinese.
e-p-armstrong/augmentoolkit
Convert Compute And Books Into Instruct-Tuning Datasets
epfLLM/Megatron-LLM
distributed trainer for LLMs
NomaDamas/awesome-korean-llm
Awesome list of Korean Large Language Models.
meta-math/MetaMath
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
jondurbin/bagel
A bagel, with everything.
UnderstandLingBV/LLaMa2lang
Convenience scripts to finetune (chat-)LLaMa3 and other models for any language
bfshi/TOAST
Official code for "TOAST: Transfer Learning via Attention Steering"
X-LANCE/UniCATS-CTX-vec2wav
[AAAI 2024] Code for CTX-vec2wav in UniCATS
Rijgersberg/GEITje
GEITje 7B: een groot open Nederlands taalmodel
abacaj/train-with-fsdp
theodorblackbird/lina-speech
lina-speech : linear attention based text-to-speech
tdrussell/qlora-pipe
A pipeline parallel training script for LLMs.
Renumics/sliceguard
A library for detecting problematic data segments in structured and unstructured data with few lines of code.
AUGMXNT/shisa
HKAB/whisper
Robust Speech Recognition via Large-Scale Weak Supervision