Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+
+# ms-marco-MiniLM-L-6-v2
+
+## Model description
+This model is a fine-tuned version of ms-marco-MiniLM-L-6-v2 for relevancy evaluation in RAG scenarios.
+
+## Training Data
+
+The model was trained on a specialized dataset for evaluating RAG responses,
+containing pairs of (context, response) with relevancy labels.
+Dataset size: 4505 training examples, 5006 validation examples.
+
+
+## Performance Metrics
+```
+
+Validation Metrics:
+- NDCG: 0.9996 ± 0.0001
+- MAP: 0.9970 ± 0.0009
+- Accuracy: 0.9766 ± 0.0033
+
+```
+
+## Usage Example
+```python
+
+from sentence_transformers import CrossEncoder
+
+# Load model
+model = CrossEncoder('xtenzr/ms-marco-MiniLM-L-6-v2_finetuned_20241120_2220')
+
+# Prepare inputs
+texts = [
+    ["Context: {...}
+Query: {...}", "Response: {...}"],
+]
+
+# Get predictions
+scores = model.predict(texts)  # Returns relevancy scores [0-1]
+
+```
+
+## Training procedure
+- Fine-tuned using sentence-transformers CrossEncoder
+- Trained on relevancy evaluation dataset
+- Optimized for RAG response evaluation

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5314fdb835fad7c742098ef73487e1d17bad82c0d9b3d14d42c670e564affaa4
+size 90866412

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}