dadelani

mamba

Mamba SSM architecture

axolotl

Go ahead and axolotl questions

Qwen2

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

alignment-handbook

Robust recipes to align language models with human and AI preferences

OLMo

Modeling, training, eval, and inference code for OLMo

GPT-4-LLM

Instruction Tuning with GPT-4

ms-swift

Use PEFT or Full-parameter to finetune 300+ LLMs or 60+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

chain-of-thought-hub

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

pyreft

ReFT: Representation Finetuning for Language Models

MEGABYTE-pytorch

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

recurrentgemma

Open weights language model from Google DeepMind, based on Griffin.

gritlm

Generative Representational Instruction Tuning

levanter

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

ALMA

State-of-the-art LLM-based translation models.

PiSSA

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models

llama2-fine-tune

Scripts for fine-tuning Llama2 via SFT and DPO.

SeaLLMs

[ACL 2024 Demo] SeaLLMs - Large Language Models for Southeast Asia

Indic-gemma-7b-Navarasa

Repository for fine-tuning gemma models using unsloth for indic languages

HebTTS

The official implementation of "A Language Modeling Approach to Diacritic-Free Hebrew TTS"

LLaMAX

latxa

Latxa: An Open Language Model and Evaluation Suite for Basque

SVFT

AdamergeX

africomet

COMET for African languages

X-Instruction

Official code and data for ACL-2024 paper "X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions"

yoruba-voice

Repo & Project for the Imminent Research Grant code & tasks

yoruba-voice-speech-recorder

App for recording speech utterances dictated from text prompts. Speaker name, audio-recording path & prompt text are saved to a metadata file. Use it for building speech recognition and speech synthesis corpora

bbc_news_scraper

anthology-bib-small

annotation-tool-frontend