Upload 8 files

added_tokens.json

@@ -0,0 +1 @@
+{"<ruby>": 32008, "<javascript>": 32007, "<NEW_LINE>": 32012, "<java>": 32003, "<python>": 32004, "<eot>": 32001, "<DEDENT>": 32014, "<mask>": 32015, "<eod>": 32000, "<comments>": 32011, "<cn>": 32010, "<php>": 32006, "<go>": 32005, "<pad>": 32002, "<INDENT>": 32013, "<en>": 32009}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "/cache/stage1_trained_models_100M/pycodegpt/",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 1,
+  "embed_dropout": 0,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.19.0",
+  "use_cache": true,
+  "vocab_size": 32016,
+  "window_size": 256
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8928cb8525adaa8b36b0afdb15d924826121596c89ef8270990e25dc2399e535
+size 272871970

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|beginoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|unkoftext|>", "pad_token": "<|padoftext|>", "additional_special_tokens": ["<eod>", "<eot>", "<pad>", "<java>", "<python>", "<go>", "<php>", "<javascript>", "<ruby>", "<en>", "<cn>", "<comments>", "<NEW_LINE>", "<INDENT>", "<DEDENT>", "<mask>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|unkoftext|>", "bos_token": "<|beginoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "/cache/stage1_trained_models_100M/pycodegpt/", "pad_token": "<|padoftext|>", "tokenizer_class": "GPT2Tokenizer"}