initialize model

README.md

@@ -1,3 +1,140 @@
 ---
+language:
+- en
 license: mit
 ---
+
+This model was trained with [Neural-Cherche](https://github.com/raphaelsty/neural-cerche). You can find details on how to fine-tune it in the [Neural-Cherche](https://github.com/raphaelsty/neural-cherche) repository.
+
+This model is an `all-mpnet-base-v2` as a ColBERT.
+
+
+```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 = models.ColBERT(
+    model_name_or_path="raphaelsty",
+    device=device,
+)
+
+retriever = retrieve.ColBERT(
+    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=3,
+)
+
+scores
+```
+
+## Ranker
+
+```python
+from neural_cherche import models, rank, retrieve
+import torch
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+batch_size = 32
+
+documents = [
+    {"id": "doc1", "title": "Paris", "text": "Paris is the capital of France."},
+    {"id": "doc2", "title": "Montreal", "text": "Montreal is the largest city in Quebec."},
+    {"id": "doc3", "title": "Bordeaux", "text": "Bordeaux in Southwestern France."},
+]
+
+queries = [
+    "What is the capital of France?",
+    "What is the largest city in Quebec?",
+    "Where is Bordeaux?",
+]
+
+retriever = retrieve.TfIdf(
+    key="id",
+    on=["title", "text"],
+)
+
+model = models.ColBERT(
+    model_name_or_path="sentence-transformers/all-mpnet-base-v2",
+    device=device,
+)
+
+ranker = rank.ColBERT(
+    key="id",
+    on=["title", "text"],
+    model=model
+)
+
+retriever_documents_embeddings = retriever.encode_documents(
+    documents=documents,
+)
+
+retriever.add(
+    documents_embeddings=retriever_documents_embeddings,
+)
+
+ranker_documents_embeddings = ranker.encode_documents(
+    documents=documents,
+    batch_size=batch_size,
+)
+
+retriever_queries_embeddings = retriever.encode_queries(
+    queries=queries,
+)
+
+ranker_queries_embeddings = ranker.encode_queries(
+    queries=queries,
+    batch_size=batch_size,
+)
+
+candidates = retriever(
+    queries_embeddings=retriever_queries_embeddings,
+    k=1000,
+)
+
+scores = ranker(
+    documents=candidates,
+    queries_embeddings=ranker_queries_embeddings,
+    documents_embeddings=ranker_documents_embeddings,
+    k=100,
+    batch_size=32,
+)
+
+scores
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "architectures": [
+    "MPNetForMaskedLM"
+  ],
+  "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,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30527
+}

linear.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c6fe3495544322ca5339d03f91afe54f6234d441f5b69b6f062f483fc9ce99
+size 394391

metadata.json

@@ -0,0 +1 @@
+{"max_length_query": 32, "max_length_document": 256, "query_prefix": "[Q] ", "document_prefix": "[D] "}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987c71696a5e133e2dad24165c4839b9cf7cf1744e30cfe4eb3a2fcd077cf4eb
+size 438097372

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": "<pad>",
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+  "cls_token": "<s>",
+  "device": "cuda",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "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]"
+}