pacman100

accelerate-deepspeed-test

Testing DeepSpeed integration in 🤗 Accelerate

accelerate-megatron-test

Testing the accelerate megatron integration

Extractive-Text-Summarization-Using-Neural-Networks

Extractive Text Summarization Using Neural Networks approaches: CNN, RNN and Linear-SVM

LLM-Workshop

LLM Workshop by Sourab Mangrulkar

Machine_Learning

Machine Learning models for Regression Tasks and Classification Tasks.

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

openhathi_instruct

This repository contains the code for dataset curation and finetuning of instruct variant of the Bilingual OpenHathi model. The resulting model is meant to follow instructions and chat in Hindi and Hinglish.

peft-codegen-25

Registration_App

This is an android app for events registration which was used for the NIT-GOA's cultural fest Raag.

pacman100/LLM-Workshop

LLM Workshop by Sourab Mangrulkar

pacman100/peft-codegen-25

pacman100/openhathi_instruct

This repository contains the code for dataset curation and finetuning of instruct variant of the Bilingual OpenHathi model. The resulting model is meant to follow instructions and chat in Hindi and Hinglish.

pacman100/mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

pacman100/peft-sd-webui-additional-networks

pacman100/acm_winter_school_gen_ai

Code for the hands-on projects for the students attending the ACM India Winter School 2023

pacman100/devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

pacman100/accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

pacman100/blog

Public repo for HF blog posts

pacman100/gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

pacman100/llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

pacman100/llm.c

LLM training in simple, raw C/CUDA

pacman100/pacman100

pacman100/pacman100.github.io

pacman100/peft-dreambooth

pacman100/peft-dreambooth-ui

An UI for Dreambooth training and inference using PEFT - Minimal, Easy to use and Adaptable.

pacman100/peft-whisper-large

pacman100/ram_efficient_fsdp

pacman100/torchtune

PyTorch native finetuning library

pacman100/twinny

The most no-nonsense locally hosted (or API hosted) AI code completion plugin for Visual Studio Code, like GitHub Copilot but 100% free and 100% private.

pacman100/bitsandbytes

8-bit CUDA functions for PyTorch

pacman100/chat-ui

Open source codebase powering the HuggingChat app

pacman100/easyllm

pacman100/hf_fsdp

A very basic fsdp wrapper for HF.

pacman100/huggingface-vscode

Code completion VSCode extension for OSS models

pacman100/llama-mistral

Inference code for Mistral and Mixtral hacked up into original Llama implementation

pacman100/llama.cpp

LLM inference in C/C++

pacman100/llama2.c

Inference Llama 2 in one file of pure C

pacman100/minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

pacman100/trl

Train transformer language models with reinforcement learning.