This model was fine-tuned to score the relevance between a query and a candidate document. It is designed for retrieval and reranking tasks such as:
The model was fine-tuned using the Hugging Face Transformers Trainer.
1from transformers import AutoTokenizer, AutoModelForSequenceClassification
2
3tokenizer = AutoTokenizer.from_pretrained(
4 "NayonAhmed09/internal-linklm"
5)
6
7model = AutoModelForSequenceClassification.from_pretrained(
8 "NayonAhmed09/internal-linklm"
9)
1from transformers import AutoTokenizer, AutoModelForSequenceClassification
2import torch
3
4tokenizer = AutoTokenizer.from_pretrained(
5 "NayonAhmed09/internal-linklm"
6)
7
8model = AutoModelForSequenceClassification.from_pretrained(
9 "NayonAhmed09/internal-linklm"
10)
11
12query = "Best moisturizer for oily skin"
13document = "A complete guide to choosing skincare products for oily skin."
14
15inputs = tokenizer(
16 query,
17 document,
18 return_tensors="pt",
19 truncation=True,
20 max_length=512
21)
22
23with torch.no_grad():
24 score = model(**inputs).logits.squeeze().item()
25
26print(score)
Higher scores indicate higher semantic relevance.
