M2-BERT 80M 8k-Retrieval

from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained(
"togethercomputer/m2-bert-80M-8k-retrieval",
trust_remote_code=True
)

max_seq_length = 8192
testing_string = "Every morning, I make a cup of coffee to start my day."
model = AutoModelForSequenceClassification.from_pretrained(
"togethercomputer/m2-bert-80M-8k-retrieval",
trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained(
"bert-base-uncased",
model_max_length=max_seq_length
)
input_ids = tokenizer(
[testing_string],
return_tensors="pt",
padding="max_length",
return_token_type_ids=False,
truncation=True,
max_length=max_seq_length
)

outputs = model(**input_ids)
embeddings = outputs['sentence_embedding']

import os
import requests

def generate_together_embeddings(text: str, model_api_string: str, api_key: str):
url = "https://api.together.xyz/api/v1/embeddings"
headers = {
"accept": "application/json",
"content-type": "application/json",
"Authorization": f"Bearer {api_key}"
}
session = requests.Session()
response = session.post(
url,
headers=headers,
json={
"input": text,
"model": model_api_string
}
)
if response.status_code != 200:
raise ValueError(f"Request failed with status code {response.status_code}: {response.text}")
return response.json()['data'][0]['embedding']

print(generate_together_embeddings(
'Hello world',
'togethercomputer/m2-bert-80M-8k-retrieval',
os.environ['TOGETHER_API_KEY'])[:10]
)