feat(llm): final code for training and saving finetuned llm model to gguf

feat(llm): final code for training and saving finetuned llm model to gguf

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

fix(notebook): remove corrupted widget states through clearing output from cells

feat(model): finetune the llama model and store in HuggingFace

feat(huggingface): update huggingface organization name to push finetuned model to, enable checkpointing

Skapades med Colab