Add model

README.md

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- ColBERT
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:497901
+- loss:Contrastive
+base_model: google/bert_uncased_L-2_H-128_A-2
+datasets:
+- sentence-transformers/msmarco-bm25
+pipeline_tag: sentence-similarity
+---
+
+# Model card for ColBERT v2 BERT Tiny
+
+This is a [ColBERT](https://github.com/stanford-futuredata/ColBERT) model finetuned from [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
+
+This model is primarily designed for unit tests in limited compute environments such as GitHub Actions. But it does work to an extent for basic use cases.

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[D] ": 30523,
+  "[Q] ": 30522
+}

artifact.metadata

@@ -0,0 +1,42 @@
+{
+    "query_token_id": "[Q] ",
+    "doc_token_id": "[D] ",
+    "query_token": "[Q] ",
+    "doc_token": "[D] ",
+    "nprobe": 2,
+    "ncandidates": 8192,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 20,
+    "similarity": "cosine",
+    "bsize": 8,
+    "accumsteps": 1,
+    "lr": null,
+    "maxsteps": null,
+    "save_every": null,
+    "resume": false,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 64,
+    "use_ib_negatives": true,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "dim": 128,
+    "doc_maxlen": 180,
+    "mask_punctuation": true,
+    "checkpoint": null,
+    "triples": null,
+    "collection": null,
+    "queries": null,
+    "index_name": null,
+    "overwrite": false,
+    "root": "",
+    "experiment": "default",
+    "index_root": null,
+    "name": "colbert-bert-tiny",
+    "rank": 0,
+    "nranks": 1,
+    "amp": false,
+    "gpus": 1,
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30524
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520fc0bc90d8bf51ddcfa05255c1b41bda0f4925577c0609d35201a5b2359814
+size 17614528

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[MASK]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "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
+    },
+    "30522": {
+      "content": "[Q] ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30523": {
+      "content": "[D] ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[MASK]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}