First Commit

README.md

@@ -0,0 +1,13 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+---
+# multi-QA_v1-mpnet-asymmetric-Q
+This is mpnet-base model trained on 1B+ question - answer pairs. 2 separate models were used for training. This model was used to encode Questions.
+
+## Usage
+The model can be used for semantic-search in conjunction with answer model : [multi-QA_v1-mpnet-asymmetric-A](https://huggingface.co/flax-sentence-embeddings/multi-QA_v1-mpnet-asymmetric-A)
+Output vectors are normalized and mean pooling used during training.

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "microsoft/mpnet-base",
+  "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,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.8.2",
+  "vocab_size": 30527
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76edbe68dc0f35ec2a07b4afb30da528f80564939776b413f31ff894165deefb
+size 438011953

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/mpnet-base", "tokenizer_class": "MPNetTokenizer"}