init commit

README.md

@@ -1,3 +1,31 @@
----
-license: mit
----
+This model has been trained without supervision following the approach described in [Towards Unsupervised Dense Information Retrieval with Contrastive Learning](https://arxiv.org/abs/2112.09118). The associated GitHub repository is available here https://github.com/facebookresearch/contriever.
+
+## Usage (HuggingFace Transformers)
+Using the model directly available in HuggingFace transformers requires to add a mean pooling operation to obtain a sentence embedding.
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained('facebook/contriever')
+model = AutoModel.from_pretrained('facebook/contriever')
+
+sentences = [
+    "Where was Marie Curie born?",
+    "Maria Sklodowska, later known as Marie Curie, was born on November 7, 1867.",
+    "Born in Paris on 15 May 1859, Pierre Curie was the son of Eugène Curie, a doctor of French Catholic origin from Alsace."
+]
+
+# Apply tokenizer
+inputs = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+outputs = model(**inputs)
+
+# Mean pooling
+def mean_pooling(token_embeddings, mask):
+    token_embeddings = token_embeddings.masked_fill(~mask[..., None].bool(), 0.)
+    sentence_embeddings = token_embeddings.sum(dim=1) / mask.sum(dim=1)[..., None]
+    return sentence_embeddings
+embeddings = mean_pooling(outputs[0], inputs['attention_mask'])
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "Contriever"
+  ],
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b6e2516913f812360475154323f50e2b1e1da0ce6a435175e08f218784c6fb
+size 438007537

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}