bhairavmehta95
on leave from my @mit EECS PhD, building B2B software. previously MS @mila-iqia. BS @umich, @nasa-jpl, @NVlabs.
@ :) New York, NY
bhairavmehta95's Stars
nomic-ai/gpt4all
gpt4all: run open-source LLMs anywhere
tloen/alpaca-lora
Instruct-tune LLaMA on consumer hardware
w-okada/voice-changer
リアルタイムボイスチェンジャー Realtime Voice Changer
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
facebookresearch/nougat
Implementation of Nougat Neural Optical Understanding for Academic Documents
OpenAccess-AI-Collective/axolotl
Go ahead and axolotl questions
astriaai/headshots-starter
InternLM/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
GerevAI/gerev
🧠 AI-powered enterprise search engine 🔎
turboderp/exllama
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
OpenPipe/OpenPipe
Turn expensive prompts into cheap fine-tuned models
ross/requests-futures
Asynchronous Python HTTP Requests for Humans using Futures
tairov/llama2.mojo
Inference Llama 2 in one file of pure 🔥
lxe/simple-llm-finetuner
Simple UI for LLM Model Finetuning
mit-han-lab/llm-awq
[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
FasterDecoding/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
waleedka/hiddenlayer
Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.
fastai/lm-hackers
Hackers' Guide to Language Models
jina-ai/finetuner
:dart: Task-oriented embedding tuning for BERT, CLIP, etc.
mit-han-lab/TinyChatEngine
TinyChatEngine: On-Device LLM Inference Library
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
johnmarktaylor91/torchlens
Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
lucidrains/q-transformer
Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind
zhenye234/CoMoSpeech
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
0nutation/USLM
Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)
dust-tt/llama-ssp
Experiments on speculative sampling with Llama models
ZhangXInFD/soundstorm-speechtokenizer
Implementation of SoundStorm built upon SpeechTokenizer.
lucidrains/diffusion-policy
Implementation of Diffusion Policy, Toyota Research's supposed breakthrough in leveraging DDPMs for learning policies for real-world Robotics
MiscellaneousStuff/PhoneLM
(R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.
KindXiaoming/Omnigrok
Omnigrok: Grokking Beyond Algorithmic Data