All files has been added...

bert_question_answering.py

@@ -0,0 +1,49 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+import gradio as gr
+
+model_name = "checkpoint-1700"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForQuestionAnswering.from_pretrained(model_name)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+def answer_question(question, context):
+    if not question.strip() or not context.strip():
+        return "Soru ve metin boş olamaz!"
+
+    inputs = tokenizer(question, context, return_tensors="pt", truncation=True)
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    answer_start = torch.argmax(outputs.start_logits)
+    answer_end = torch.argmax(outputs.end_logits) + 1
+
+    input_ids = inputs["input_ids"][0]
+    answer = tokenizer.convert_tokens_to_string(
+        tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end].cpu())
+    )
+
+    return answer.strip()
+
+demo = gr.Interface(
+    fn=answer_question,
+    inputs=[
+        gr.Textbox(label="Soru", placeholder="Örn: Türkiye'nin başkenti neresidir ?"),
+        gr.Textbox(
+            label="Metin", 
+            placeholder="Metni buraya girin...",
+            lines=10
+        )
+    ],
+    outputs=gr.Textbox(label="Cevap"),
+    title="BERT Soru-Cevap Sistemi",
+    description="Metin ve sorunuzu girin ve BERT modeli cevabı metin içerisinden çıkarsın.",
+    theme="default",
+)
+
+if __name__ == "__main__":
+    demo.launch()

checkpoint-1700/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-1700/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b05b8c64e566185dea3939a20c6b7ab5f2a6949828cfb90b745762b46c4850
+size 440136504

checkpoint-1700/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "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]"
+}

requirements.txt

@@ -0,0 +1,3 @@
+gradio 
+transformers
+torch