Mihaiii/semantic-autocomplete
A blazing-fast semantic search React component. Match by meaning, not just by letters. Search as you type without waiting (no debounce needed). Rank by cosine similarity.
Repositories
Mihaiii/LLaMA-Omni
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
Mihaiii/llm_steer
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
Mihaiii/backtrack_sampler
An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
Mihaiii/nanochat
The best ChatGPT that $100 can buy.
Mihaiii/NegotiateBench
Letting LLMs negotiate against each other
Mihaiii/parameter-golf
Train the smallest LM you can that fits in 16MB. Best model wins!
Mihaiii/trivia
A live multiplayer trivia game where users can bid for the subject of the next question
Mihaiii/llama.cpp
Port of Facebook's LLaMA model in C/C++
Mihaiii/TimeStampBuddy
A bot that provides Youtube vid chapters on Twitter (a.k.a. X )
Mihaiii/Ovis
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
Mihaiii/ActuosusAI
AI management tool
Mihaiii/first2apply
Mihaiii/json-schema-logits-processor
Mihaiii/laser
The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
Mihaiii/token_forge
Mihaiii/antislop-sampler
Mihaiii/scrappysoloserialmicroentrepreneur
Mihaiii/guidance
A guidance language for controlling large language models.
Mihaiii/fasthtml
The fastest way to create an HTML app
Mihaiii/fastRAG
Efficient Retrieval Augmentation and Generation Framework
Mihaiii/CommonGen-Eval
Evaluating LLMs with CommonGen-Lite
Mihaiii/detect-pretrain-code-contamination
Mihaiii/LLamaSharp
C#/.NET binding of llama.cpp, including LLaMa/GPT model inference and quantization, ASP.NET core integration and UI.
Mihaiii/sparsegpt-for-LLaMA
Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.
Mihaiii/RoAlpaca
Finetuning InstructLLaMA with portuguese data
Mihaiii/RoverNavigator
Homework assignment made on 07.09.2021. Had 3h to complete.
Mihaiii/LearningClojure
Mihaiii/ic-wall
Crossover Ethereum/Internet Computer dApp demo and proof of concept. Sign in using Metamask, link eth address to IC identity FTW! ∞