Fabio Matricardi's repositories
How-I-Built-a-Chatbot-that-Crushed-ChatGPT
Repo of the code from the Medium article
My-2B-Reflection-LLM
How to build your own Reflection LLM with only 2B parameters model
danube3-0.5b-chat
stramlit AI assistant with llamacpp and H2O danube3
135M-you-cannot-go-Smaller
Repo of the code from the Medium article 135M: you cannot go Smaller
AI-ExtractData-NuExtract-tiny
NuExtract-tiny GGUF for data extraction in json format
Gemma2-9b-GradioClient
Run with API call to Hugging Face Spaces Gemma2-9B model
llamaCPP_Agents
Run AI agents with llama-cpp-agents locally
llamacppChatDocs
Chat with your documents using only LlamaCPP and Langchain
Gemma2-2b-it-chatbot
Repo of the code from the Medium article about running Gemma2 2b locally
-LLM-Studies
Collection of Resources, repositories and snippets for LLM and Open source Generative AI
OpenVINO-vs-GGGUF-battle
Repo with code in the prompt battle between CPU inference with OpenVINO and llamaCPP
OuteWorlderAI
How to run LiteMistral150M on your PC
qwen2.5-1.5b-testbench
run GGUF qwen2.5-1.5b with llamaCPP-python
TensorOpera-Fox-1-chat
Chat with web-based Document search and TensorOpera Fox-1 LlamaCPP
77M-chatbot-is-reality
Run encoder-decoder LaMini-Flan-T5 with streamlit
buildLLMapplicationFree
Repo of the code from the Medium article about Valentina Alto's book
FivePythonSkills
Cracking the AI Code: 5 Python fundamentals is all you need.
FourHacksLlamaCPP
Four hacks to run LLMs with your CPU
Gemma-The-Writer-9B_localGPT
A full fledged Writer assistant with LlamaCPP and python on your Local PC
gitHub-instructions
guide for local repo alignment
llama3.2-1b-it_test
DIY benchmark testing with Llama3.2-1B-instruct and streamlit
OPENVINO-betterStreamer
Textual Interface for Gemma2-2B Openvino with streaming effect
OpenVINO-Gemma2B-streamlit
Using OpenVINO with Gemma2-2B INT4 and streamlit CHAT APP
openvino-Lamini
test openvino
PersonalMoE
My personal Attempt to Mixture of Experts with llama-cpp-python
Qwen1.5to2.5compare
Compare NLP tasks on Qwen1.5, Qwen2 and Qwen2.5 using llamaCPP and 1.5B/1.8B GGUF models
Streamlit-Gemma2B-Reflection
Stramlit interface for Reflection2B - a Gemma2-2B-it prompt hack
SuperLiteLLMs
super Lite LLMs
ultraSmolLM
On the normal human benchmark models smaller than 500M parameters
YouAreTheBenchmark
Personal Catalog of prompt templates for NLP tasks