new model gpt-2-medium

added_tokens.json

@@ -1 +1 @@
-{"<|EOS|>": 50258, "<|PAD|>": 50260, "<|SEP|>": 50261, "<|BOS|>": 50257, "<|UNK|>": 50259}
+{"<|BOS|>": 50257, "<|SEP|>": 50261, "<|PAD|>": 50260, "<|EOS|>": 50258, "<|UNK|>": 50259}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "gpt2-medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,18 +8,22 @@
   "bos_token_id": 50257,
   "embd_pdrop": 0.1,
   "eos_token_id": 50258,
-  "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_embd": 1024,
+  "n_head": 16,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 24,
   "n_positions": 1024,
+  "n_special": 0,
   "pad_token_id": 50260,
+  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
   "sep_token_id": 50261,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -32,7 +36,8 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.5.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
   "use_cache": true,
   "vocab_size": 50262
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660de74540a53ac7032a003526b675624e137b7e78bacbeefa14a7312b371ef4
-size 510423675
+oid sha256:9ef249e0689873c1c19be0b64fc2df7ec0c02edc0397207fcab07027d8f82033
+size 1444601791

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2-medium", "tokenizer_class": "GPT2Tokenizer"}