MD 2 JSON with T5 small

README.md

@@ -0,0 +1,71 @@
+# MD2JSON-T5-V1: Text-to-JSON Converter with T5
+
+This model utilizes the **T5 (Text-to-Text Transfer Transformer)** architecture to convert text strings into valid JSON objects. It is designed to take structured text and transform it into a JSON object.
+
+## Description
+
+The **MD2JSON-T5-V1** model is trained to interpret text strings where keys and values are separated by a colon (e.g., `#firstname: John`), and then convert them into a valid JSON object. This model can be used for a wide range of tasks where converting text to JSON is required.
+
+### Example Input:
+- Input: 
+    ```text
+    #firstname: John
+    #lastname: Doe
+    #age: 30
+    #married: true
+    #hobbies: ["gaming", "running"]
+    #address: {"city": "Berlin", "zipcode": 10115}
+    #url: "https://example.com"
+    ```
+
+- Generated JSON Output:
+    ```json
+    {
+        "firstname": "John",
+        "lastname": "Doe",
+        "age": 30,
+        "married": true,
+        "hobbies": ["gaming", "running"],
+        "address": {
+            "city": "Berlin",
+            "zipcode": 10115
+        },
+        "url": "https://example.com"
+    }
+    ```
+
+### Another Example:
+- Input: 
+    ```text
+    #name: Charlie
+    #age: 29
+    #isStudent: true
+    #skills: ["Java", "Machine Learning"]
+    #profile: {"github": "charlie29", "linkedin": "charlie-linkedin"}
+    #height: 172.3
+    ```
+
+- Generated JSON Output:
+    ```json
+    {
+        "name": "Charlie",
+        "age": 29,
+        "isStudent": true,
+        "skills": ["Java", "Machine Learning"],
+        "profile": {
+            "github": "charlie29",
+            "linkedin": "charlie-linkedin"
+        },
+        "height": 172.3
+    }
+    ```
+
+## Load the Model
+
+To use the model and perform inference, follow the steps below:
+
+### Install Dependencies
+
+```bash
+pip install torch transformers datasets
+

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7347a0168f05074991fb6713e04ec84dba64e0467ab0fbeca9f062ce8a81e9
+size 242041896

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47aa9fc06bb7be77be36d5b2141aafdfa79160d1335b92af37270b5777ac1811
+size 484159866

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf11243288a5c23a3ff457eb797018d98049d17a92086a1b2f6131f32cc6fa6
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2128056c0e422c6e1201ad40cceec048820717e61f000141d547bd956d6b7131
+size 1064

trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 20,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 812050808832.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bb76d3e0c05f47eddf1629ac30c18510adf5139cf3fdf8ae1cc76e1fd7a14e
+size 5304