upload model

README.md

@@ -1,3 +1,64 @@
 ---
+language:
+- en
 license: mit
 ---
+
+This model was trained with [Neural-Cherche](https://github.com/raphaelsty/neural-cherche). You can find details on how to fine-tune it in the [Neural-Cherche](https://github.com/raphaelsty/neural-cherche) repository.
+
+
+```sh
+pip install neural-cherche
+```
+
+## Retriever
+
+```python
+from neural_cherche import models, retrieve
+import torch
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+batch_size = 32
+
+documents = [
+    {"id": 0, "document": "Food"},
+    {"id": 1, "document": "Sports"},
+    {"id": 2, "document": "Cinema"},
+]
+
+queries = ["Food", "Sports", "Cinema"]
+
+model = SparseEmbed(
+    model_name_or_path="raphaelsty/neural-cherche-sparse-embed",
+    device=device,
+)
+
+retriever = retrieve.SparseEmbed(
+    key="id",
+    on=["document"],
+    model=model,
+)
+
+documents_embeddings = retriever.encode_documents(
+    documents=documents,
+    batch_size=batch_size,
+)
+
+retriever = retriever.add(
+    documents_embeddings=documents_embeddings,
+)
+
+queries_embeddings = retriever.encode_queries(
+    queries=queries,
+    batch_size=batch_size,
+)
+
+scores = retriever(
+    queries_embeddings=queries_embeddings,
+    batch_size=batch_size,
+    k=100,
+    k_ranker=10,
+)
+
+scores
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "raphaelsty/neural-cherche-sparse-embed",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

linear.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd1265d36bedccc9ef3e4329d46510010a908257867a21840e46ec8c3a45f9f
+size 394391

metadata.json

@@ -0,0 +1,10 @@
+{
+    "max_length_query": 64,
+    "max_length_document": 256,
+    "query_prefix": "",
+    "document_prefix": "",
+    "padding": "max_length",
+    "truncation": true,
+    "add_special_tokens": true,
+    "n_mask_tokens": 3
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28d2cd97f79d1a6d5f6ef3a4f2e5e022b9c293dd982e29c7cc21ef9dfe9bbfd
+size 438080896

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 +1,58 @@
+{
+  "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]",
+  "device": "cuda",
+  "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]"
+}