初始化项目，由ModelHub XC社区提供模型

Model: CausalNLP/gpt2-multilingual-20-zh-repair_3epochs
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 +1,106 @@
+---
+library_name: transformers
+base_model: CausalNLP/gpt2-hf_multilingual-20
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-multilingual-20-zh-repair_3epochs
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gpt2-multilingual-20-zh-repair_3epochs
+
+This model is a fine-tuned version of [CausalNLP/gpt2-hf_multilingual-20](https://huggingface.co/CausalNLP/gpt2-hf_multilingual-20) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5681
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 3.5916        | 0.0626 | 500   | 3.6450          |
+| 3.6159        | 0.1252 | 1000  | 3.6299          |
+| 3.5824        | 0.1879 | 1500  | 3.6205          |
+| 3.5986        | 0.2505 | 2000  | 3.6152          |
+| 3.5522        | 0.3131 | 2500  | 3.6103          |
+| 3.5757        | 0.3757 | 3000  | 3.6064          |
+| 3.5319        | 0.4384 | 3500  | 3.6034          |
+| 3.6002        | 0.5010 | 4000  | 3.6007          |
+| 3.5922        | 0.5636 | 4500  | 3.5978          |
+| 3.5069        | 0.6262 | 5000  | 3.5957          |
+| 3.5616        | 0.6889 | 5500  | 3.5933          |
+| 3.4412        | 0.7515 | 6000  | 3.5917          |
+| 3.5299        | 0.8141 | 6500  | 3.5897          |
+| 3.4957        | 0.8767 | 7000  | 3.5882          |
+| 3.574         | 0.9393 | 7500  | 3.5863          |
+| 3.6165        | 1.0019 | 8000  | 3.5852          |
+| 3.5208        | 1.0645 | 8500  | 3.5844          |
+| 3.5485        | 1.1271 | 9000  | 3.5829          |
+| 3.5339        | 1.1897 | 9500  | 3.5816          |
+| 3.5774        | 1.2524 | 10000 | 3.5802          |
+| 3.5327        | 1.3150 | 10500 | 3.5790          |
+| 3.4909        | 1.3776 | 11000 | 3.5780          |
+| 3.5583        | 1.4402 | 11500 | 3.5768          |
+| 3.5347        | 1.5029 | 12000 | 3.5755          |
+| 3.5236        | 1.5655 | 12500 | 3.5744          |
+| 3.4773        | 1.6281 | 13000 | 3.5733          |
+| 3.5296        | 1.6907 | 13500 | 3.5726          |
+| 3.4551        | 1.7534 | 14000 | 3.5718          |
+| 3.5473        | 1.8160 | 14500 | 3.5710          |
+| 3.5095        | 1.8786 | 15000 | 3.5704          |
+| 3.5057        | 1.9412 | 15500 | 3.5700          |
+| 3.5425        | 2.0038 | 16000 | 3.5695          |
+| 3.5358        | 2.0664 | 16500 | 3.5695          |
+| 3.4944        | 2.1290 | 17000 | 3.5692          |
+| 3.4901        | 2.1916 | 17500 | 3.5690          |
+| 3.4932        | 2.2543 | 18000 | 3.5688          |
+| 3.5356        | 2.3169 | 18500 | 3.5686          |
+| 3.5352        | 2.3795 | 19000 | 3.5683          |
+| 3.4779        | 2.4421 | 19500 | 3.5682          |
+| 3.5639        | 2.5047 | 20000 | 3.5682          |
+| 3.4919        | 2.5674 | 20500 | 3.5681          |
+| 3.5491        | 2.6300 | 21000 | 3.5681          |
+| 3.5216        | 2.6926 | 21500 | 3.5681          |
+| 3.4751        | 2.7552 | 22000 | 3.5681          |
+| 3.4998        | 2.8179 | 22500 | 3.5681          |
+| 3.4943        | 2.8805 | 23000 | 3.5681          |
+| 3.4764        | 2.9431 | 23500 | 3.5681          |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.0
+- Datasets 4.4.1
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "block_size": 1024,
+  "bos_token_id": 3,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 4,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 119547
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 3,
+  "eos_token_id": 4,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c857d649cf27756fb230ba002fd02be7f8b7360ea57030adc91be3ec4711b059
+size 355324096

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece41235fdf7f47bf13c7d512a3c0f834b3c9cf8db0828a4b7ed0bdb57fa9406
+size 5841