Initial commit

README.md

@@ -1,3 +1,41 @@
 ---
 license: apache-2.0
 ---
+
+# Beam Retrieval: General End-to-End Retrieval for Multi-Hop Question Answering (Zhang et all 2023)
+
+Unofficial mirror of [Beam Retriever](https://github.com/canghongjian/beam_retriever)
+
+This is the finetuned **encoder only** of the Beam Retriever model which can be used for maximum inner product search.
+
+## Usage
+
+```python
+from transformers import DebertaV2Model
+
+finetuned_encoder = DebertaV2Model.from_pretrained('scholarly-shadows-syndicate/beam_retriever_unofficial_encoder_only')
+```
+
+## Citations
+
+```bibtex
+@article{Zhang2023BeamRG,
+  title={Beam Retrieval: General End-to-End Retrieval for Multi-Hop Question Answering},
+  author={Jiahao Zhang and H. Zhang and Dongmei Zhang and Yong Liu and Sheng Huang},
+  journal={ArXiv},
+  year={2023},
+  volume={abs/2308.08973},
+  url={https://api.semanticscholar.org/CorpusID:261030563}
+}
+```
+
+```bibtex
+@article{He2020DeBERTaDB,
+  title={DeBERTa: Decoding-enhanced BERT with Disentangled Attention},
+  author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen},
+  journal={ArXiv},
+  year={2020},
+  volume={abs/2006.03654},
+  url={https://api.semanticscholar.org/CorpusID:219531210}
+}
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2Model"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c783a10446bb851a58769cb22681c707f0308f616b973cb8f5c384b3a6e5941
+size 1736180262