Update README with Modelfile requirement for Ollama usage

Add Ollama Modelfile with Llama 3.1 chat template fix

Add Usage with Transformers section to README

Add README with model details

Add Q3_K_M GGUF quantization

Add Q4_K_M GGUF quantization

Add Q6_K GGUF quantization

Add Q8_0 GGUF quantization

Add abliterated bf16 model from deepseek-ai/DeepSeek-R1-Distill-Llama-70B

initial commit