Upload folder using huggingface_hub

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2_small_AR_superbpe_32768_parallel3-100_42",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 32768,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 32768,
+  "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": 128,
+  "pad_token_id": 1,
+  "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
+    }
+  },
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32769
+}

meta.json

@@ -0,0 +1,8 @@
+{
+     "total_bytes": 10000000000,
+     "train_files": [
+          "/root/xiulinyang/multilingual-tokenization/data/parallel3-100/AR/train/AR.txt",
+          "/root/xiulinyang/multilingual-tokenization/data/parallel3-100/AR/train/AR.txt",
+          "/root/xiulinyang/multilingual-tokenization/data/parallel3-100/AR/train/AR_truncated_2724431626.txt"
+     ]
+}