Gavi Narra's repositories
mlx-whatsapp
An mlx project to train a base model on your whatsapp chats using (Q)Lora finetuning
home_control
An idea how to use guidance to generate specific api
chatgpt-markdown
Converts chatgpt exported data to markdown so you can use it in Obsidian
micrograd_cs
Based on Video Lecture by karpathy but in CSharp
mnist
A comparison of mnist between various types of training
DeepSeek-VL
DeepSeek-VL: Towards Real-World Vision-Language Understanding
fine-tune-mistral
Fine-tune mistral-7B on 3090s, a100s, h100s
GEOSwift
The Swift Geometry Engine.
jsoncanvas
An open file format for infinite canvas data.
LLM-As-Chatbot
LLM as a Chatbot Service
llm.c
LLM training in simple, raw C/CUDA
mlx-examples
Examples in the MLX framework
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
netron
Visualizer for neural network, deep learning and machine learning models
openai
OpenAI .NET sdk - ChatGPT, Whisper, GPT-3, GPT-4, Azure OpenAI and DALL-E
openai-python
The official Python library for the OpenAI API
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
sqlite-vss
A SQLite extension for efficient vector search, based on Faiss!
superset
Apache Superset is a Data Visualization and Data Exploration Platform
text-generation-webui
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
WebGPT
Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~2000 lines of vanilla Javascript.