thefirehacker

binaryen

Compiler infrastructure and toolchain library for WebAssembly

emscripten

Emscripten: An LLVM-to-WebAssembly Compiler

pyodide

Python with the scientific stack, compiled to WebAssembly.

AIOne

MLOne Powered by AIEdX. Machine Learning Course for Everyone. Tier1 Basic

bubblspace

anymat2vec

Any chemical composition -> word2vec vector.

Generating-Knowledge-Bases-From-Scientific-Publications

Sarvam_ShukaV1_Demo

TimeCapsule-SLM

AI creative coding studio Deepresearch , blogs , Animation all in browser full privacy.

thefirehacker/TimeCapsule-SLM

AI creative coding studio Deepresearch , blogs , Animation all in browser full privacy.

thefirehacker/Sarvam_ShukaV1_Demo

thefirehacker/avataRL

rl from zero pretrain, can it be done? we'll see.

thefirehacker/Complex-Function-Analysis

thefirehacker/csm

A Conversational Speech Generation Model

thefirehacker/Cursor-Django

Learn how to build your first full stack web app with English and Cursor AI

thefirehacker/DeepGEMM

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

thefirehacker/gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

thefirehacker/HHEMVictorious

Unhallucinate Challenge: 24 Hours Fight

thefirehacker/HiddenLayerLens

deep dive into the internal representations of open-source large language models (LLMs)

thefirehacker/infinite

a rubric driven prioritized replay rl algo to maximise continual learning

thefirehacker/llama

Inference code for LLaMA models

thefirehacker/llama-agentic-system

Agentic components of the Llama Stack APIs

thefirehacker/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.

thefirehacker/LLMJsonMode_FuncCalling

Json Mode and Func calling Testing for various LLM and LLM endpoint

thefirehacker/MarketAgents

A distributed agent orchestration framework for market agents

thefirehacker/modded-nanogpt

NanoGPT (124M) in 3 minutes

thefirehacker/nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

thefirehacker/nanogpt-speedrun

NanoGPT (124M) as fast as possible

thefirehacker/outlines

Structured Text Generation

thefirehacker/ParntQuestAI

ParentQuest

thefirehacker/punjabi-data-collection

Punjabi Data Collection project

thefirehacker/PureRL

LM/VLM implementations

thefirehacker/RAGEN

RAGEN is the first open-source reproduction of DeepSeek-R1 on AGENT training.

thefirehacker/readme-ai

README file generator, powered by large language model APIs 👾

thefirehacker/s1

s1: Simple test-time scaling

thefirehacker/streamlit-dataview

Streamlit viewer for GW data

thefirehacker/Tensor-Slayer

Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic interpretability

thefirehacker/text-to-lora

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

thefirehacker/thefirehacker.github.io