Upload Tevatron-Elastic checkpoint (final model)

README.md

@@ -0,0 +1,29 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+library_name: transformers
+tags:
+- tevatron
+- tevatron-elastic
+- information-retrieval
+- retriever
+- elastic
+---
+
+# tevatron-elastic-bert-retriever-depth
+
+A **retriever** trained with [Tevatron-Elastic](https://github.com/zhichaoxu-shufe/tevatron-elastic),
+which trains one checkpoint to serve many operating points along the depth / width / token
+compression axes. This checkpoint is an elastic **depth** axis (early exit): one checkpoint serves several layer counts.
+
+- **Base model:** `google-bert/bert-base-uncased`
+- **Task:** retriever
+- **Elastic axis:** depth
+- **Training data:** [rlhn/rlhn-680K](https://huggingface.co/datasets/rlhn/rlhn-680K), max length 512, `query:`/`passage:` prefixes.
+
+Full-point BEIR-15 nDCG@10: **0.453**.
+
+Load with the Tevatron-Elastic framework and select an operating point with `prune_to` /
+`encode_at`; see the repository for usage. Part of a release of 20 checkpoints (3 backbones,
+retrieval and reranking, all compression axes) accompanying the Tevatron-Elastic paper. Reported as
+a reproducibility resource, not a state-of-the-art claim.

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "bfloat16",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

granularities.json

@@ -0,0 +1,36 @@
+{
+  "pooling": "cls",
+  "normalize": true,
+  "points": [
+    {
+      "layer": 2,
+      "dim": 768,
+      "name": null
+    },
+    {
+      "layer": 4,
+      "dim": 768,
+      "name": null
+    },
+    {
+      "layer": 6,
+      "dim": 768,
+      "name": null
+    },
+    {
+      "layer": 8,
+      "dim": 768,
+      "name": null
+    },
+    {
+      "layer": 10,
+      "dim": 768,
+      "name": null
+    },
+    {
+      "layer": 12,
+      "dim": 768,
+      "name": null
+    }
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1721649bfc11530ed1e09b35dc3c45310ec98b182a28499e29f134cc3c654d8c
+size 218986904

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}