llama4
deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
- 8.4k
- Python
- Apache-2.0
- 8 wk ago
Llama-4-Scout-17B-16E-Instruct
Image text to text model, used with transformers.
Gated access
- 1.4k
- 110k
- other
- 18 mo ago
llm-architecture-from-scratch
Implementing LLM architectures from scratch in PyTorch
- 856
- Python
- BSD-3-Clause
- 24 h ago
Llama-Prompt-Guard-2-86M
Text classification model, used with transformers.
Gated access
- 395
- 90k
- other
- 19 mo ago
parsemypdf
Collection of PDF parsing libraries like AI based docling, claude, openai, gemini, meta's llama-vision, unstructured-io, and pdfminer, pymupdf, pdfplumber etc for efficient snapshot, text, table, and metadata extraction.
- 196
- Python
- MIT
- 2 mo ago
Llama-4-Scout-17B-16E
Image text to text model, used with transformers.
Gated access
- 281
- 1.8k
- other
- 20 mo ago
mcore-bridge
MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.3, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.8, Qwen3-Omni, Gemma4, ...).
- 107
- Python
- Apache-2.0
- 14 h ago
BarkSuckerbird
A powerful Telegram AI bot that integrates multiple AI models, live web search via DuckDuckGo + Groq, and an admin texting system. It’s designed for 24/7 uptime using Flask’s keep-alive mechanism — perfect for deployment on Replit, Render, Koyeb or Railway.
- 3
- Python
- MIT
- 2 mo ago
Multilingual-Invoice-Parsing-with-LLaMA-4
Combining OCR for text extraction with LLMs for accurate, efficient document structuring.
- 1
- Python
- 19 mo ago
Llama4
Llama4 – Code from Scratch This project is inspired by [vukrosic’s courses repository](https://github.com/vukrosic/courses). Here, I’ve implemented the tokenizer logic from scratch using Python and Google Colab to better understand how LLMs handle text at the token level.
- 0
- Jupyter Notebook
- 17 mo ago






