初始化项目，由ModelHub XC社区提供模型

Model: CausalNLP/gpt2-multilingual-20-arabic-repair_3epochs_lr1e-4_bf16
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 +1,96 @@
+---
+library_name: transformers
+base_model: CausalNLP/gpt2-hf_multilingual-20
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-multilingual-20-arabic-repair_3epochs_lr1e-4_bf16
+  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-arabic-repair_3epochs_lr1e-4_bf16
+
+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: 3.2206
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Use 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_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 3.295         | 0.0799 | 500   | 3.3488          |
+| 3.2752        | 0.1597 | 1000  | 3.3363          |
+| 3.2844        | 0.2396 | 1500  | 3.3416          |
+| 3.3059        | 0.3194 | 2000  | 3.3491          |
+| 3.335         | 0.3993 | 2500  | 3.3387          |
+| 3.2845        | 0.4791 | 3000  | 3.3301          |
+| 3.2458        | 0.5590 | 3500  | 3.3216          |
+| 3.2689        | 0.6388 | 4000  | 3.3129          |
+| 3.2737        | 0.7187 | 4500  | 3.3069          |
+| 3.2604        | 0.7985 | 5000  | 3.3000          |
+| 3.2255        | 0.8784 | 5500  | 3.2936          |
+| 3.239         | 0.9582 | 6000  | 3.2882          |
+| 3.2594        | 1.0380 | 6500  | 3.2832          |
+| 3.2123        | 1.1179 | 7000  | 3.2780          |
+| 3.2347        | 1.1977 | 7500  | 3.2726          |
+| 3.2197        | 1.2776 | 8000  | 3.2671          |
+| 3.2028        | 1.3574 | 8500  | 3.2615          |
+| 3.195         | 1.4373 | 9000  | 3.2557          |
+| 3.2049        | 1.5171 | 9500  | 3.2510          |
+| 3.1649        | 1.5970 | 10000 | 3.2458          |
+| 3.1984        | 1.6768 | 10500 | 3.2409          |
+| 3.2787        | 1.7567 | 11000 | 3.2374          |
+| 3.1966        | 1.8365 | 11500 | 3.2334          |
+| 3.166         | 1.9164 | 12000 | 3.2305          |
+| 3.2029        | 1.9962 | 12500 | 3.2272          |
+| 3.1629        | 2.0760 | 13000 | 3.2268          |
+| 3.1115        | 2.1559 | 13500 | 3.2253          |
+| 3.184         | 2.2357 | 14000 | 3.2239          |
+| 3.1391        | 2.3156 | 14500 | 3.2229          |
+| 3.1341        | 2.3954 | 15000 | 3.2220          |
+| 3.1623        | 2.4753 | 15500 | 3.2214          |
+| 3.1565        | 2.5551 | 16000 | 3.2211          |
+| 3.1129        | 2.6350 | 16500 | 3.2208          |
+| 3.2043        | 2.7148 | 17000 | 3.2207          |
+| 3.1044        | 2.7947 | 17500 | 3.2206          |
+| 3.1922        | 2.8746 | 18000 | 3.2206          |
+| 3.1229        | 2.9544 | 18500 | 3.2206          |
+
+
+### Framework versions
+
+- Transformers 4.57.4
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.2
+- Tokenizers 0.22.2

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": "4.57.4",
+  "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": "4.57.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb3e7921f2350d97438c676b560410411570ba368bff062a5be9b95144d72ba
+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 sha256:2c1218a8aadc309ac9aa78ed71bf2dcd2e66326cee9bf066379ef474d90723b8
+size 5905