ok

README.md

@@ -0,0 +1,92 @@
+## How to use
+
+```python
+import logging
+from simpletransformers.seq2seq import Seq2SeqModel, Seq2SeqArgs
+
+logging.basicConfig(level=logging.INFO)
+transformers_logger = logging.getLogger("transformers")
+transformers_logger.setLevel(logging.WARNING)
+
+model_args = Seq2SeqArgs()
+
+# 加载本地训练好的模型
+model = Seq2SeqModel(
+    encoder_decoder_type="bart",
+    encoder_decoder_name="NTUYG/SOTitle-java-BART",
+    args=model_args,
+)
+
+describe = """
+I am a beginner at Android Java development but I have a few years of school + uni experience in Java. I am trying to write to a text file in an assets folder in my app using FileOutputStream but it doesn't seem to write to it at all since I am using InputStream to read the file after and there haven't any updates. Here is my code
+"""
+code = """
+private void updateTextFile(String update) {
+    FileOutputStream fos = null;
+
+    try
+    {
+        fos = openFileOutput("Questions",MODE_PRIVATE);
+        fos.write("Testing".getBytes());
+    } 
+    catch (FileNotFoundException e) 
+    {
+        e.printStackTrace();
+    } 
+    catch (IOException e) 
+    {
+        e.printStackTrace();
+    } 
+    finally 
+    {
+        if(fos!=null)
+        {
+            try 
+            {
+                fos.close();
+            } 
+            catch (IOException e) 
+            {
+                e.printStackTrace();
+            }
+        }
+    }
+
+    String text = "";
+
+    try
+    {
+        InputStream is = getAssets().open("Questions");
+        int size = is.available();
+        byte[] buffer = new byte[size];
+        is.read(buffer);
+        is.close();
+        text = new String(buffer);
+    } 
+    catch (IOException e) 
+    {
+        e.printStackTrace();
+    }
+    System.out.println("Tesing output " + text);
+}
+"""
+
+from nltk import word_tokenize
+
+describe = describe.replace('\n',' ').replace('\r',' ')
+describe = ' '.join(word_tokenize(describe))
+code = code.replace('\n',' ').replace('\r',' ')
+code = ' '.join(word_tokenize(code))
+
+# human ： Java Android Cant seem to update text file using FileOutputStream
+
+body = describe + ' <code> ' + code +' </code>'
+print(
+    model.predict(
+        [
+            body
+        ]
+    )
+)
+```
+

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": false,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "transformers_version": "4.2.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "best_model_dir": "with_code/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": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "facebook/bart-large", "model_type": "bart", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 50, "optimizer": "AdamW", "output_dir": "with_code/", "overwrite_output_dir": true, "process_count": 10, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 4000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 4, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 45000, "weight_decay": 0.0, "model_class": "Seq2SeqModel", "base_marian_model_name": "facebook/bart-large", "dataset_class": null, "do_sample": false, "early_stopping": true, "evaluate_generated_text": true, "length_penalty": 2.0, "max_length": 20, "max_steps": -1, "num_beams": 1, "num_return_sequences": 1, "repetition_penalty": 1.0, "top_k": null, "top_p": null, "use_multiprocessed_decoding": false, "src_lang": "en_XX", "tgt_lang": "ro_RO"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207a4aec91dfe4ca63a2b3bf90abfe54b29f9084e4eb365b78339f0b826d0e27
+size 1625568367

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024, "name_or_path": "facebook/bart-large"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4e0726acd6192d6c8abc13417d2b0d63d26e54f0b0c6904c80f118fa221e36
+size 2991