Update README.md

README.md

@@ -50,7 +50,41 @@ Although this model performs well and is state-of-the-art for now. But still thi
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+Example Code for Scoring Query-Document Pairs:
+In an IR setting, you provide a query and one or more candidate documents. The model scores each document for relevance to the query, which can be used for ranking.
+```
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import torch
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("Mavkif/urdu-mt5-mmarco")
+model = AutoModelForSeq2SeqLM.from_pretrained("Mavkif/urdu-mt5-mmarco")
+
+# Define the query and candidate documents
+query = "پاکستان کی معیشت کی موجودہ صورتحال کیا ہے؟"
+document_1 = "پاکستان کی معیشت میں حالیہ ترقی کے بارے میں معلومات۔"
+document_2 = "فٹبال پاکستان میں تیزی سے مقبول ہو رہا ہے۔"
+
+# Tokenize query-document pairs and calculate relevance scores
+def get_score(query, document):
+    input_text = f"Query: {query} Document: {document}"
+    inputs = tokenizer(input_text, return_tensors="pt", truncation=True)
+    
+    # Pass through the model and get the relevance score (logits)
+    outputs = model(**inputs)
+    score = outputs.logits[0, -1, :]  # last token logits
+    return torch.softmax(score, dim=0)[tokenizer.eos_token_id].item()
+
+# Get scores for each document
+score_1 = get_score(query, document_1)
+score_2 = get_score(query, document_2)
+
+print(f"Relevance Score for Document 1: {score_1}")
+print(f"Relevance Score for Document 2: {score_2}")
+
+# Higher score indicates higher relevance
+
+```
 
 
 
@@ -68,7 +102,6 @@ MRR @10 : 0.247
 
 
 ### Results
-## Detailed Results
 
 | Model                                 | Name                                  | Data         | Recall@10 | MRR@10 | Queries Ranked |
 |---------------------------------------|---------------------------------------|--------------|-----------|--------|----------------|
@@ -79,46 +112,22 @@ MRR @10 : 0.247
 | This work                             | Mavkif/urdu-mt5-mmarco                | Urdu data    | 0.438     | 0.247  | 6980           |
 
 
-#### Summary
 
 
 
 ### Model Architecture and Objective
-From config.json :
-
 {
-  "_name_or_path": "unicamp-dl/mt5-base-mmarco-v2",
-  "architectures": [
-    "MT5ForConditionalGeneration"
-  ],
-  "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "mt5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
-  "use_cache": true,
-  "vocab_size": 250112
+    "_name_or_path": "unicamp-dl/mt5-base-mmarco-v2",
+    "architectures": ["MT5ForConditionalGeneration"],
+    "d_model": 768,
+    "num_heads": 12,
+    "num_layers": 12,
+    "dropout_rate": 0.1,
+    "vocab_size": 250112,
+    "model_type": "mt5",
+    "transformers_version": "4.38.2"
 }
+For more details on how to customize the decoding parameters (such as max_length, num_beams, and early_stopping), refer to the Hugging Face documentation.
 
 
 ## Model Card Authors [optional]