Init Model

README.md

@@ -0,0 +1,37 @@
+---
+license: cc-by-nc-4.0
+language:
+- en
+tags:
+- English
+- Bert-base
+- Text Classification
+pipeline_tag: text-classification
+---
+
+# RoBERTa base Fine-Tuned for Proposal Sentence Classification
+
+## Overview
+
+- **Language**: English
+- **Model Name**: oeg/BERT-Repository-Proposal
+  
+## Description
+
+This model is a fine-tuned bert base uncased model trained to classify sentences into two classes: proposal and non-proposal sentences. The training data includes sentences proposing a software or data repository. The model is trained to recognize and classify these sentences accurately.
+
+## How to use
+
+To use this model in Python:
+
+```python
+from transformers import RobertaForSequenceClassification, RobertaTokenizer
+import torch
+
+tokenizer = RobertaTokenizer.from_pretrained("bert-repo-proposal-tokenizer")
+model = RobertaForSequenceClassification.from_pretrained("bert-repo-proposal-model")
+
+sentence = "Your input sentence here."
+inputs = tokenizer(sentence, return_tensors="pt")
+outputs = model(**inputs)
+probabilities = torch.nn.functional.softmax(outputs.logits, dim=1)

bert-repo-proposal-model/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/models2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

bert-repo-proposal-model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:297228d77b137ccb9f141024bcdf6bba70ec08f5416c38b4e3de910ef86f5e63
+size 437958648

bert-repo-proposal-tokenizer/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

bert-repo-proposal-tokenizer/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}