config and tokenizer

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "hidden_dropout_prob": 0.0,
+  "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": 2,
+  "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,
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 31
+}

tokenizer.json

@@ -0,0 +1,57 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "<|endoftext|>": 0,
+      " A": 1,
+      " B": 2,
+      " C": 3,
+      " D": 4,
+      " E": 5,
+      " F": 6,
+      " G": 7,
+      " H": 8,
+      " I": 9,
+      " J": 10,
+      " K": 11,
+      " L": 12,
+      " M": 13,
+      " N": 14,
+      " O": 15,
+      " P": 16,
+      " Q": 17,
+      " R": 18,
+      " S": 19,
+      " T": 20,
+      " U": 21,
+      " V": 22,
+      " W": 23,
+      " X": 24,
+      " Y": 25,
+      " Z": 26,
+      " a": 27,
+      " b": 28,
+      " c": 29,
+      " d": 30
+    },
+    "merges": []
+  }
+}