Upload 13 files

.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

README.md

@@ -1,3 +1,46 @@
----
-license: apache-2.0
----
+# Quintu/bge-m3-legal_retrieval
+
+This repository contains the **Quintu/bge-m3-legal_retrieval**, a fine-tuned version of the **bge-m3** model optimized for legal document retrieval tasks. The model is specifically designed to handle the nuances of legal language, enabling accurate and efficient retrieval of relevant legal documents based on semantic similarity.
+
+## Model Details
+
+- **Base Model**: [bge-m3](https://huggingface.co/BAAI/bge-m3-base)
+- **Task**: Legal Document Retrieval
+- **Fine-tuning Dataset**: Legal documents and associated queries from real-world legal scenarios.
+- **Framework**: [Sentence-Transformers](https://www.sbert.net/)
+
+## Key Features
+
+- **Legal Language Understanding**: Optimized to understand legal terms, context, and phrases.
+- **Semantic Search**: Retrieves documents based on meaning, not just keywords.
+- **High Precision Retrieval**: Tailored for legal professionals and researchers.
+
+## How to Use
+
+### Load the Model
+
+You can easily load and use the model with the `SentenceTransformer` library:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Load the fine-tuned model
+model_tuned = SentenceTransformer("Quintu/bge-m3-legal_retrieval")
+
+# Example usage: Encode queries and documents
+queries = ["What are the key legal precedents for intellectual property disputes?"]
+documents = [
+    "This document discusses key precedents in intellectual property law.",
+    "This document covers legal principles in criminal law."
+]
+
+# Encode the queries and documents
+query_embeddings = model_tuned.encode(queries)
+document_embeddings = model_tuned.encode(documents)
+
+# Compute similarity (example with cosine similarity)
+from sklearn.metrics.pairwise import cosine_similarity
+similarity_scores = cosine_similarity(query_embeddings, document_embeddings)
+
+# Output similarity scores
+print(similarity_scores)

colbert_linear.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2448a6548db0f14df36a908308a029d0ceab0d396766c73a4cef450001592cf
+size 2100674

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/kaggle/input/checkpoint-18200/checkpoint-18200",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

latest

@@ -0,0 +1 @@
+global_step5200

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a3a02b42bade05c28d970e22a92793fbaea430fd6c91f5bb6a149aad4395ae
+size 1135554344

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f937cd91ec5f097a4a2caca6ce6777c37430b85e18c4f272e42eaad55a5579b
+size 14512

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9f3f66d244fd57cbe0c397ba1d7f96dc0bbff2d693738e3e471ecf0c911b89
+size 14512

sentencepiece.bpe.model

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

sparse_linear.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00ab7de6fbc33480ed5463a51c088fda900aaceb565f30e0e6dd6beb54bc7cd
+size 3516

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c4143f5a2a1aeb18b8e71fb320266a4b65f3e2923ba6cb16a19b53a2058731
+size 17083204

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 400,
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b457a2620fe61116caa14dd6ae2a73e3d409a6393c55ba3f8a923a45e9f6ed
+size 7032