Upload 12 files

app.py

@@ -0,0 +1,32 @@
+import streamlit as st
+from simpletransformers.question_answering import QuestionAnsweringModel
+
+# Load your model
+model_path = "best_model"
+model = QuestionAnsweringModel("bert", model_path, use_cuda=False)
+
+# Streamlit app
+st.title("Question Answering Model (Bert Base Cased Squad2)")
+
+# Input fields
+context = st.text_area("Context:")
+question = st.text_input("Question:")
+
+# Prediction button
+if st.button("Predict"):
+    to_predict = [{"context": context, "qas": [{"question": question, "id": "0"}]}]
+    try:
+        answers, _ = model.predict(to_predict, n_best_size=1)
+        if answers and 'answer' in answers[0]:
+            st.text("Answer:")
+            st.write(f"<span style='color:cyan; font-weight:bold'>{answers[0]['answer'][0]}</span>", unsafe_allow_html=True)
+        else:
+            st.text("No answer found.")
+    except Exception as e:
+        st.error(f"An error occurred: {str(e)}")
+
+
+st.header("Sample Context:")
+st.write("During the Renaissance period in Europe, the Medici family played a crucial role in fostering artistic and intellectual advancements. Their patronage of artists and scholars in Florence contributed significantly to the flourishing of Renaissance culture.")
+st.write(f"Question: <span style='color:yellow;'>What family was influential during the Renaissance?</span>", unsafe_allow_html=True)
+st.write(f"Answer: <span style='color:red;'>Medici family</span>", unsafe_allow_html=True)

best_model/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "deepset/bert-base-cased-squad2",
+  "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,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "name": "Bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

best_model/eval_results.txt

@@ -0,0 +1,4 @@
+correct = 4
+eval_loss = -7.323484897613525
+incorrect = 0
+similar = 1

best_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9feed26beea398e936d3822679ca4520acb63b210828dd5d1e6a3c152ad25fb9
+size 430908208

best_model/model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "bert_outputs/bert/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "correct", "early_stopping_metric_minimize": false, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 1000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "deepset/bert-base-cased-squad2", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 100, "optimizer": "AdamW", "output_dir": "outputs/bert", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 6, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": true, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 18, "weight_decay": 0.0, "model_class": "QuestionAnsweringModel", "doc_stride": 384, "lazy_loading": false, "max_answer_length": 100, "max_query_length": 64, "n_best_size": 8, "null_score_diff_threshold": 0.0, "special_tokens_list": []}

best_model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4caa07c657a1ac0d662188d28a42d3a7e370ed5467509ea5e57c8b8762982496
+size 861930618

best_model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664c0974659943d2d01281d3cc23bfa2ff082f81c647a502e2596687a6312ce9
+size 1064

best_model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

best_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": false,
+  "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]"
+}

best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8f12778aa88cdaa7f1e9f1f7a8a60a303e2f3cb2e072bbfacdc69809ebd704
+size 3512

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+simpletransformers
+torch
+transformers