using config and tokenizer from gpt-2 orig

added_tokens.json

@@ -1,4 +0,0 @@
-{
-  "<|pad|>": 50258,
-  "<|startoftext|>": 50257
-}

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,18 +7,15 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "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,
   "resid_pdrop": 0.1,
-  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -31,7 +27,5 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.8.2",
-  "use_cache": true,
-  "vocab_size": 50259
+  "vocab_size": 50257
 }

special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|pad|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}