fix: updates to newer version of llama.cpp

[gphorvath]

• Fixed name changes in newer llama.cpp
  • LLAMA_CUBLAS --> GGML_CUDA
  • convert-hf-to-gguf.py --> convert_hf_to_gguf.py
  • llama.cpp/quantize --> llama.cpp/llama-quantize
  • llama.cpp/main --> llama.cpp/llama-cli
• Pinned llama.cpp to the most recent release tag to avoid drift in the future.
• Fixed typo: Orignal vs Original
• Added .gitignore to make sure tutorial directories and python artifacts aren't checked in

[gphorvath]

Thank you for the tutorial! I fixed a couple issues as I worked through caused by some drift in llama.cpp and a typo. If this isn't helpful, feel free to close!