Upload folder using huggingface_hub

README.md

@@ -0,0 +1,16 @@
+---
+license: apache-2.0
+language:
+  - en
+base_model:
+  - OpenSciLM/OpenScholar_Retriever
+---
+
+neophyte-retriever is a continued pre-trained version of [OpenSciLM/OpenScholar_Retriever](https://huggingface.co/OpenSciLM/OpenScholar_Retriever) for scientific literature synthesis.
+
+### Model Description
+
+- **Developed by:** Bio Protocol
+- **Model type:** a masked language model.
+- **Language(s) (NLP):** English
+- **Date cutoff:** The pre-training data is mixture of [neophyte-faiss-index-v1](https://huggingface.co/datasets/bio-protocol/neophyte-faiss-index-v1), [peS2o](https://huggingface.co/datasets/allenai/peS2o), [CCNews](https://huggingface.co/datasets/vblagoje/cc_news) and [Proofpile2](https://huggingface.co/datasets/EleutherAI/proof-pile-2).

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:fb5226976e362e070ad5b3f6c5bd38ed03a770b7d349b9334e4db8d61cc5f8fa
+size 435633182

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"}