anordin95/run-llama-locally

Run and explore Llama models locally with minimal dependencies on CPU

168 best points · 36 comments · 6 Hacker News posts · 188 GitHub stars · View on GitHub

Hacker News discussions

• Run Llama locally with only PyTorch on CPU (168 points, 34 comments, by anordin95, 2024-10-08)
• Directly run and investigate Llama models locally (8 points, 1 comments, by anordin95, 2024-10-03)
• Run Llama locally on CPU with minimal API's in-between you and the model (3 points, 0 comments, by anordin95, 2024-09-30)
• Directly run and explore Llama models (3 points, 0 comments, by anordin95, 2024-10-04)
• Directly run and investigate Llama models locally with only PyTorch (3 points, 1 comments, by anordin95, 2024-10-09)
• Run Llama locally with minimal dependencies (2 points, 0 comments, by anordin95, 2024-10-01)