llama3

Use google sheets as a gui for crewAI

Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.

This application uses LLMs like DeepSeek, GPT-5, Claude, Gemini or Llama, Mixtral (locally) in order to generate text based on the user input. The user input is used to retrieve relevant information from the database and then the retrieved information is used to generate the text. This approach combines power of LLMs and access to source documen

Shinkai allows you to create AI agents without touching code. Define tasks, schedule actions, and let Shinkai write custom code for you. Native crypto support included.

LLM Code (Open Claude Code) is an agentic coding tool that lives in your terminal, understands your codebase and helps you code faster through natural language commands

Private RAG app sample using Llama3, Ollama and PostgreSQL

Local RAG app chat, search and analyse PDF files

Create synthetic datasets for training and testing Language Learning Models (LLMs) in a Question-Answering (QA) context.

Running llama3 using Ollama-Python, Curl, LangChain, Chroma, and User interface.

Minimal CPU-only Ollama Docker Image

Chat with your Documents(PDF, TXT, DOCX, ODT, PPTX etc), Websites and Youtube Chat too!, CSV files. Uses langchain, Ollama, Groq, Gemini, Streamlit. Llama3 available

Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.

Interact with OpenAI and OpenAI-compatible chat completion APIs in a simple and elegant way. Supports Cohere V2, Groq, Ollama, OpenRouter, Together AI, Perplexity, and more.

Code for Deep Learning for Modern AI

Multimodal Instruction Tuning for Llama 3

Easy "1-line" calling of all LLMs from OpenAI, MS Azure, AWS Bedrock, GCP Vertex, and Ollama

📤 Email Classification and Automatic Re-routing with the power of LLMs and Distributed Task Queues. 🏆 Winner at Barclays Hack-O-Hire 2024!

Named Entity Recognition with an decoder-only (autoregressive) LLM using HuggingFace

Train Llama 3 models from scratch. Any scale, any personality. By Arianna Method.

Fully Configurable RAG Pipeline for Bengali Language RAG Applications. Supports both Local and Huggingface Models, Built with Langchain.