Pinned Loading

1. llama-cpp-python-wheels llama-cpp-python-wheels Public

   Pre-built wheels for llama-cpp-python across platforms and CUDA versions

   14 1

2. llama_32_3b_instruct_launcher llama_32_3b_instruct_launcher Public

   Quick and dirty launcher scripts for Llama-3.2-3B-Instruct using HuggingFace Transformers. Includes full version with optimizations and bare-bones minimal version. Just update the model path and run.

   Python

3. llama_32_3b_instruct_launcher_gguf llama_32_3b_instruct_launcher_gguf Public

   Quick and dirty launcher scripts for Llama-3.2-3B-Instruct GGUF models using llama-cpp-python. Includes full version with optimizations and bare-bones minimal version. Just update the model path an…

   Python

4. llama_32_3b_instruct_launcher_gguf_metal llama_32_3b_instruct_launcher_gguf_metal Public

   Quick and dirty macOS launcher for Llama-3.2-3B-Instruct GGUF models with Metal GPU acceleration. Optimized for Apple Silicon (M1/M2/M3/M4). Just compile with Metal support, update the model path, …

   Python

5. llama_32_3b_instruct_launcher_langchain llama_32_3b_instruct_launcher_langchain Public

   Quick and dirty LangChain launcher for Llama-3.2-3B-Instruct GGUF models. Minimal setup using LangChain abstractions with streaming chat. Just update the model path and run.

   Python

6. llama_32_3b_instruct_launcher_ollama llama_32_3b_instruct_launcher_ollama Public

   Quick and dirty Ollama launcher for Llama-3.2-3B-Instruct. Uses Ollama API for automatic model management and hardware optimization. Just install Ollama, pull the model, and run.

   Python