Upload SearchMap Preview model with complete configuration

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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

@@ -1,3 +1,141 @@
----
-license: mit
----
+---
+language: en
+tags:
+- embedding
+- transformers
+- search
+- e-commerce
+- conversational-search
+- semantic-search
+license: mit
+pipeline_tag: feature-extraction
+---
+
+# VectorPath SearchMap: Conversational E-commerce Search Embedding Model
+
+## Model Description
+
+SearchMap is a specialized embedding model designed to revolutionize e-commerce search by making it more conversational and intuitive. Fine-tuned on the Stella Embed 400M v5 base model, it excels at understanding natural language queries and matching them with relevant products.
+
+## Key Features
+
+- Optimized for conversational e-commerce queries
+- Handles complex, natural language search intents
+- Supports multi-attribute product search
+- Efficient 1024-dimensional embeddings (configurable up to 8192)
+- Specialized for product and hotel search scenarios
+
+## Model Details
+
+- Base Model: Stella Embed 400M v5
+- Embedding Dimensions: Configurable (512, 768, 1024, 2048, 4096, 6144, 8192)
+- Training Data: 100,000+ e-commerce products across 32 categories
+- License: MIT
+- Framework: PyTorch / Sentence Transformers
+
+## Usage
+
+### Using FlagEmbedding (Recommended)
+
+```python
+from FlagEmbedding import FlagModel
+
+# Initialize the model
+model = FlagModel(
+    'vectorpath/searchmap-v1',
+    query_instruction_for_retrieval="Generate a representation for this search query that can be used to retrieve related ecommerce products:",
+    use_fp16=True
+)
+
+# Encode queries
+query = "A treat my dog and I can eat together"
+query_embedding = model.encode(query)
+
+# Encode products
+product_description = "Organic peanut butter dog treats, safe for human consumption..."
+product_embedding = model.encode(product_description)
+```
+
+### Using with FAISS for Vector Search
+
+```python
+import numpy as np
+import faiss
+
+# Create FAISS index
+embedding_dimension = 1024  # or your chosen dimension
+index = faiss.IndexFlatL2(embedding_dimension)
+
+# Add product embeddings
+product_embeddings = model.encode(product_descriptions)
+index.add(np.array(product_embeddings).astype('float32'))
+
+# Search
+query_embedding = model.encode(query)
+distances, indices = index.search(
+    np.array([query_embedding]).astype('float32'), 
+    k=10
+)
+```
+
+### Example Search Queries
+
+The model excels at understanding natural language queries like:
+- "A treat my dog and I can eat together"
+- "Lightweight waterproof hiking backpack for summer trails"
+- "Eco-friendly kitchen gadgets for a small apartment"
+- "Comfortable shoes for standing all day at work"
+
+## Performance and Limitations
+
+### Strengths
+- Excellent at understanding conversational and natural language queries
+- Strong performance in e-commerce and hotel search scenarios
+- Handles complex multi-attribute queries
+- Efficient computation with configurable embedding dimensions
+
+### Current Limitations
+- May not fully prioritize weighted terms in queries
+- Limited handling of slang and colloquial language
+- Regional language variations might need fine-tuning
+
+## Training Details
+
+The model was trained using:
+- Supervised learning with FlagEmbedding
+- 100,000+ product dataset across 32 categories
+- AI-generated conversational search queries
+- Positive and negative product examples for contrast learning
+
+## Intended Use
+
+This model is designed for:
+- E-commerce product search and recommendations
+- Hotel and accommodation search
+- Product catalog vectorization
+- Semantic similarity matching
+- Query understanding and intent detection
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{vectorpath2025searchmap,
+  title={SearchMap: Conversational E-commerce Search Embedding Model},
+  author={VectorPath Research Team},
+  year={2025},
+  publisher={Hugging Face},
+  journal={HuggingFace Model Hub},
+}
+```
+
+## Contact and Community
+
+- Discord Community: [Join our Discord]
+- GitHub Issues: Report bugs and feature requests
+- Email: [Contact Email]
+
+## License
+
+This model is released under the MIT License. See the LICENSE file for more details.

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./saved_model/checkpoint-21660",
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration.NewConfig",
+    "AutoModel": "modeling.NewModel"
+  },
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pack_qkv": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 160000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "unpad_inputs": true,
+  "use_memory_efficient_attention": true,
+  "vocab_size": 30528
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.42.4",
+    "pytorch": "2.4.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f8474dad9b263d78420f3e1cc540d6160c32539f946feefe90727806fbf934
+size 1736585680

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,64 @@
+{
+  "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]",
+  "max_length": 8000,
+  "model_max_length": 32768,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}