The Easiest and Cheapest Way to Deploy Finetuned Mistral 7B Instruct Model (or Any Model) | by Qendel AI - Freedium
Thu Nov 30 2023 00:07:24 GMT+0000 (Coordinated Universal Time)
Saved by
@mikeee
Copy
# Mount your drive
drive.mount('/content/drive')
# Define the data type
dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16
# Your finetuned model's path (either in google drive or local)
model_path = "/path/to/your/finetuned/model/"
# Load the finetuned model and tokenizer
finetuned_model = AutoPeftModelForCausalLM.from_pretrained(
model_path,
low_cpu_mem_usage=True,
torch_dtype=dtype,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(model_path)
content_copyCOPY
https://freedium.cfd/https://medium.com/@qendelai/the-easiest-and-cheapest-way-to-deploy-finetuned-mistral-7b-instruct-model-or-any-model-3f236182e8b8
Comments