first model commit

added_tokens.json

@@ -0,0 +1 @@
+{"<BOS>": 50257, "<EOS>": 50258, "<PAD>": 50259}

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "vocab_size": 50260
+}

eval_results_lm.txt

@@ -0,0 +1 @@
+perplexity = 15.180801570535857

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42034309104044362acb046ab50c9092a693d75587563b4cc702bc89123df4f5
+size 510415775

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<BOS>", "eos_token": "<EOS>", "unk_token": "<|endoftext|>", "pad_token": "<PAD>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e79fa3cdbfec333beafbfb704db1bb0c94bfef7f56cd0ac64a35b55b7791b0
+size 1263