| The [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) model has been quantized using [AutoRound](https://github.com/intel/auto-round) and serialized in the GPTQ format at 4-bit precision, resulting in a 70% reduction in size while maintaining 99% of its original accuracy. | |
| This quantization process was conducted by [Sofya](https://www.sofya.ai/). | |
| ### How to run | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| quantized_model = "sofya-ai/Meta-Llama-3.1-70B-Instruct-int4-auto-gptq" | |
| model = AutoModelForCausalLM.from_pretrained(quantized_model, | |
| device_map="auto") | |
| tokenizer = AutoTokenizer.from_pretrained(quantized_model) | |
| text = "The patient was admitted to the hospital" | |
| inputs = tokenizer(text, return_tensors="pt").to(model.device) | |
| print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50)[0])) | |
| ``` |