Upload latest checkpoint with model card

README.md

@@ -0,0 +1,44 @@
+
+# Model Card for t5_small Summarization Model
+
+## Model Details
+This model is a fine-tuned version of t5_small on the CNN/Daily Mail dataset
+for summarization tasks.
+
+## Training Data
+The model was trained on the CNN/Daily Mail dataset.
+
+## Training Procedure
+- **Learning Rate**: 5e-5
+- **Epochs**: 3
+- **Batch Size**: 16
+
+## How to Use
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+tokenizer = AutoTokenizer.from_pretrained("hskang/cnn_dailymail_t5_small")
+model = AutoModelForSeq2SeqLM.from_pretrained("hskang/cnn_dailymail_t5_small")
+
+input_text = "upstage tutorial text summarization code"
+inputs = tokenizer.encode(input_text, return_tensors="pt")
+outputs = model.generate(inputs)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Evaluation
+- **ROUGE-1**: 23.45
+- **ROUGE-2**: 7.89
+- **ROUGE-L**: 21.34
+- **BLEU**: 13.56
+
+## Limitations
+The model may generate biased or inappropriate content due to the nature
+of the training data.
+It is recommended to use the model with caution and apply necessary filters.
+
+## Ethical Considerations
+Bias: The model may inherit biases present in the training data.
+Misuse: The model can be misused to generate misleading or harmful content.
+Copyright and License
+This model is licensed under the MIT License.

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.2"
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}