Initial commit: Upload fine-tuned XLM-R Large reranker for PersianSciQA

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1 @@
- cross-encoder
- reranker
- persian
- farsi
- xlm-roberta
- scientific-qa
- PersianSciQA
---
- **Base Model:** `xlm-roberta-large`
- **Task:** Reranking / Sentence Similarity
- **Fine-tuning Framework:** `sentence-transformers`
- **Language:** Persian (fa)
+---
    "بازیابی اطلاعات یک فرآیند پیچیده است که شامل شاخص گذاری و جستجوی اسناد می شود. ارزیابی آن اغلب با معیارهایی مانند دقت و بازیابی انجام می شود.", # "Information retrieval is a complex process involving indexing and searching documents. Its evaluation is often done with metrics like precision and recall."
    "یادگیری عمیق در سال های اخیر پیشرفت های چشمگیری در پردازش زبان طبیعی داشته است.", # "Deep learning has made significant progress in natural language processing in recent years."
    "این مقاله به بررسی روش های جدید برای ارزیابی سیستم های بازیابی اطلاعات معنایی می پردازد و معیارهای نوینی را معرفی می کند." # "This paper examines new methods for evaluating semantic information retrieval systems and introduces novel metrics."
    print(f"Score: {scores[i]:.4f}\t Document: {documents[i]}")
  title={PersianSciQA: A new Dataset for Bridging the Language Gap in Scientific Question Answering},
  author={Anonymous},
  year={2025},
  booktitle={Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP)},
  note={Confidential review copy. To be updated upon publication.}

README.md

@@ -0,0 +1 @@
- cross-encoder
- reranker
- persian
- farsi
- xlm-roberta
- scientific-qa
- PersianSciQA
---
- **Base Model:** `xlm-roberta-large`
- **Task:** Reranking / Sentence Similarity
- **Fine-tuning Framework:** `sentence-transformers`
- **Language:** Persian (fa)
+---
    "بازیابی اطلاعات یک فرآیند پیچیده است که شامل شاخص گذاری و جستجوی اسناد می شود. ارزیابی آن اغلب با معیارهایی مانند دقت و بازیابی انجام می شود.", # "Information retrieval is a complex process involving indexing and searching documents. Its evaluation is often done with metrics like precision and recall."
    "یادگیری عمیق در سال های اخیر پیشرفت های چشمگیری در پردازش زبان طبیعی داشته است.", # "Deep learning has made significant progress in natural language processing in recent years."
    "این مقاله به بررسی روش های جدید برای ارزیابی سیستم های بازیابی اطلاعات معنایی می پردازد و معیارهای نوینی را معرفی می کند." # "This paper examines new methods for evaluating semantic information retrieval systems and introduces novel metrics."
    print(f"Score: {scores[i]:.4f}\t Document: {documents[i]}")
  title={PersianSciQA: A new Dataset for Bridging the Language Gap in Scientific Question Answering},
  author={Anonymous},
  year={2025},
  booktitle={Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP)},
  note={Confidential review copy. To be updated upon publication.}

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "sentence_transformers": {
+    "activation_fn": "torch.nn.modules.activation.Sigmoid",
+    "version": "4.1.0"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval/CrossEncoderCorrelationEvaluator_validation-eval_results.csv

@@ -0,0 +1,5 @@
+epoch,steps,Pearson_Correlation,Spearman_Correlation
+1.0,1990,0.9083937104078955,0.9041493991660567
+2.0,3980,0.9149564252595215,0.9116139336307938
+1.0,1990,0.9050290793513027,0.9028359853877621
+2.0,3980,0.9155049366399222,0.9112594866045101

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65f4a73dcdc052bc527cd1f13577d09f58e77317b189ad05c7199179c4b9ac0
+size 2239614572

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}