File size: 698 Bytes
c0b5eff
5ba152f
c0b5eff
 
 
5ba152f
2255cd8
c0b5eff
5ba152f
 
 
 
 
 
c0b5eff
5ba152f
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
from datasets import load_dataset
from sentence_transformers import SentenceTransformer, util

def evaluate_model(model_name):
    try:
        model = SentenceTransformer(model_name)
        dataset = load_dataset("arshiaafshani/persian-natural-fluently", split="train[:2]")

        scores = []
        for row in dataset:
            emb1 = model.encode(row["instruction"], convert_to_tensor=True)
            emb2 = model.encode(row["output"], convert_to_tensor=True)
            sim_score = float(util.cos_sim(emb1, emb2)[0])
            scores.append(sim_score)

        return sum(scores) / len(scores)
    except Exception as e:
        print(f"Evaluation failed: {e}")
        return None