Upload sentence-transformers/all-mpnet-base-v2 for document encoding in RAG systems

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,100 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+- rag
+- document-embedding
+base_model: sentence-transformers/all-mpnet-base-v2
+license: apache-2.0
+---
+
+# Document Encoder for RAG - MPNet Base V2
+
+This is a **sentence-transformers** model based on **sentence-transformers/all-mpnet-base-v2**. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+## Model Details
+
+- **Base Model**: sentence-transformers/all-mpnet-base-v2
+- **Embedding Dimension**: 768
+- **Max Sequence Length**: 384 tokens
+- **Use Case**: Document encoding for RAG (Retrieval-Augmented Generation) systems
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Load model
+model = SentenceTransformer('azizdh00/MNLP_M2_document_encoder')
+
+# Encode documents
+documents = [
+    "This is a sample document about artificial intelligence.",
+    "Machine learning is a subset of AI that uses algorithms.",
+    "Natural language processing enables computers to understand text."
+]
+
+embeddings = model.encode(documents)
+print(f"Embeddings shape: {embeddings.shape}")
+```
+
+## Usage (HuggingFace Transformers)
+
+You can also use the model without sentence-transformers:
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained('azizdh00/MNLP_M2_document_encoder')
+model = AutoModel.from_pretrained('azizdh00/MNLP_M2_document_encoder')
+
+# Tokenize and encode
+def encode_text(texts):
+    encoded = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
+    with torch.no_grad():
+        outputs = model(**encoded)
+    # Mean pooling
+    embeddings = outputs.last_hidden_state.mean(dim=1)
+    return embeddings
+
+# Example usage
+texts = ["Sample document text"]
+embeddings = encode_text(texts)
+```
+
+## Training Data
+
+This model was originally trained on a large dataset of sentence pairs for semantic similarity tasks.
+
+## Performance
+
+The model achieves strong performance on:
+- Semantic similarity tasks
+- Document retrieval
+- Clustering tasks
+- Information retrieval benchmarks
+
+## Technical Details
+
+- **Model Type**: Sentence Transformer (MPNet)
+- **Training Procedure**: Pre-trained on sentence similarity tasks
+- **Intended Uses**: Semantic search, clustering, similarity measurement
+- **Languages**: Primarily English
+
+## License
+
+This model is released under the Apache 2.0 License.

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.3",
+    "pytorch": "2.7.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3c8c717335c801abb15983036a6f1df4b6943fd6b93717969efd96d22eeec6
+size 437967672

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

rag_config.json

@@ -0,0 +1,14 @@
+{
+  "model_name": "sentence-transformers/all-mpnet-base-v2",
+  "embedding_dimension": 768,
+  "max_sequence_length": 384,
+  "pooling_mode": "mean",
+  "normalize_embeddings": true,
+  "use_case": "document_encoding_for_rag",
+  "compatible_with": [
+    "faiss",
+    "chromadb",
+    "pinecone",
+    "weaviate"
+  ]
+}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 384,
+  "do_lower_case": false
+}

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_config.json

@@ -0,0 +1,73 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}