初始化项目，由ModelHub XC社区提供模型

Model: DavidLanz/uuu_fine_tune_gpt2
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+license: gpl
+model_name: GPT2
+model_type: GPT2
+language: en
+pipeline_tag: text-generation
+tags:
+- pytorch
+- gpt
+- gpt2
+---
+
+
+# Fine-tuning GPT2 with energy plus medical dataset
+
+Fine tuning pre-trained language models for text generation.
+
+Pretrained model on Chinese language using a GPT2 for Large Language Head Model objective.
+
+## Model description
+
+transferlearning from DavidLanz/uuu_fine_tune_taipower and fine-tuning with medical dataset for the GPT-2 architecture.
+
+### How to use
+
+You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
+set a seed for reproducibility:
+
+```python
+>>> from transformers import GPT2LMHeadModel, BertTokenizer, TextGenerationPipeline
+
+>>> model_path = "DavidLanz/DavidLanz/uuu_fine_tune_gpt2"
+>>> model = GPT2LMHeadModel.from_pretrained(model_path)
+>>> tokenizer = BertTokenizer.from_pretrained(model_path)
+
+>>> max_length = 200
+>>> prompt = "歐洲能源政策"
+>>> text_generator = TextGenerationPipeline(model, tokenizer)
+>>> text_generated = text_generator(prompt, max_length=max_length, do_sample=True)
+>>> print(text_generated[0]["generated_text"].replace(" ",""))
+```
+
+```python
+>>> from transformers import GPT2LMHeadModel, BertTokenizer, TextGenerationPipeline
+
+>>> model_path = "DavidLanz/DavidLanz/uuu_fine_tune_gpt2"
+>>> model = GPT2LMHeadModel.from_pretrained(model_path)
+>>> tokenizer = BertTokenizer.from_pretrained(model_path)
+
+>>> max_length = 200
+>>> prompt = "蕁麻疹過敏"
+>>> text_generator = TextGenerationPipeline(model, tokenizer)
+>>> text_generated = text_generator(prompt, max_length=max_length, do_sample=True)
+>>> print(text_generated[0]["generated_text"].replace(" ",""))
+```

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 101,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 102,
+  "gradient_checkpointing": false,
+  "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,
+  "pad_token_id": null,
+  "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
+    }
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_class": "BertTokenizerFast",
+  "transformers_version": "5.10.2",
+  "use_cache": false,
+  "vocab_size": 21128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "eos_token_id": 102,
+  "transformers_version": "5.10.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18fc244b666ffdb72098681ee8b054abb43e8fb9880dd6ab66deeffee1156fc
+size 408289920

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898d3cf80083b1933906a8f70608212ac847c26ffce233757f05691c2a82d24e
+size 408323418

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10df04fe4e6fd00f491a886be60b543610153c77d66f8c1ea5c958932a6401e0
+size 5201