Resolve tokenizer issues and uploaded new quantized GGUF models

Delete tokenizer_config.json

Delete tokenizer.json

Delete special_tokens_map.json

Delete ggml-model-Q5_K_M.gguf

Delete ggml-model-Q4_K_M.gguf

Upload ggml-model-Q5_K_M.gguf

Upload ggml-model-Q4_K_M.gguf

Update README.md

Add lora adapter model

Add logs

Upload tokenizer

Upload PhiForCausalLM

initial commit