pip install -U torch==2.3.1+cpu --extra-index-url https://download.pytorch.org/whl/cpu
pip install -U transformers==4.42.4 intel-extension-for-pytorch==2.3.100

import torch
from transformers import AutoTokenizer, AutoModel
import intel_extension_for_pytorch as ipex

def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded,
                        1) / torch.clamp(input_mask_expanded.sum(1),
                                        min=1e-9)

# load model
tokenizer = AutoTokenizer.from_pretrained('Intel/intel-optimized-model-for-embeddings-v1')
model = AutoModel.from_pretrained('Intel/intel-optimized-model-for-embeddings-v1', 
                                   torchscript=True)
model.eval()

# do IPEX optimization
batch_size = 1
seq_length=512
vocab_size = model.config.vocab_size
sample_input = {"input_ids": torch.randint(vocab_size, size=[batch_size, seq_length]),
                "token_type_ids": torch.zeros(size=[batch_size, seq_length],
                                                dtype=torch.int),
                "attention_mask": torch.randint(1, size=[batch_size, seq_length])}
text = "This is a test."
model = ipex.optimize(model, level="O1",auto_kernel_selection=True,
                            conv_bn_folding=False, dtype=torch.bfloat16)

with torch.no_grad(), torch.cpu.amp.autocast(cache_enabled=False,
                                                dtype=torch.bfloat16):
    # Compile model
    model = torch.jit.trace(model, example_kwarg_inputs=sample_input,
                                    check_trace=False, strict=False)
    model = torch.jit.freeze(model)
    
    # Call model
    tokenized_text = tokenizer(text, padding=True, truncation=True, return_tensors='pt')
    model_output = model(**tokenized_text)
    sentence_embeddings = mean_pooling(model_output,tokenized_text['attention_mask'])
    embeddings = sentence_embeddings[0].tolist()

# Embeddings output
print(embeddings)