Pinned Repositories
build-nanogpt
Video+code lecture on building nanoGPT from scratch
efficient-vits-finetuning
Finetuning VITS Efficiently
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
spotifyFlacDL
Downloads FLAC audio files from public Spotify playlists
nivibilla's Repositories
nivibilla/build-nanogpt
Video+code lecture on building nanoGPT from scratch
nivibilla/efficient-vits-finetuning
Finetuning VITS Efficiently
nivibilla/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
nivibilla/spotifyFlacDL
Downloads FLAC audio files from public Spotify playlists
nivibilla/StyleTTS-VC
Official Implementation of StyleTTS-VC
nivibilla/CS909
nivibilla/dukascopy-npm-docker
nivibilla/EfficientHTR
EfficientNet-B7 for Offline Handwriting Recognition by Transfer Learning
nivibilla/exllama
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
nivibilla/exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
nivibilla/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
nivibilla/CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
nivibilla/EAGLE
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
nivibilla/icetk
A unified tokenization tool for Images, Chinese and English.
nivibilla/litellm
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
nivibilla/llama-cpp-python
Python bindings for llama.cpp
nivibilla/llama.cpp
Port of Facebook's LLaMA model in C/C++
nivibilla/MARS5-TTS
MARS5 speech model (TTS) from CAMB.AI
nivibilla/mergekit
Tools for merging pretrained large language models.
nivibilla/qlora-fine-tune
nivibilla/REST_Prices
nivibilla/Retrieval-based-Voice-Conversion-WebUI
Voice data <= 10 mins can also be used to train a good VC model!
nivibilla/sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
nivibilla/StyleTTS
Official Implementation of StyleTTS
nivibilla/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
nivibilla/torchtune
A Native-PyTorch Library for LLM Fine-tuning
nivibilla/TradeCopy
Processes NSE EOD data to MetaStock ASCII (7 column) format
nivibilla/trl
Train transformer language models with reinforcement learning.
nivibilla/trt-llm-as-openai
This reference can be used with any existing OpenAI integrated apps to run with TRT-LLM inference locally on GeForce GPU on Windows instead of cloud.
nivibilla/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs