added vocab/tokenizer related files

added_tokens.json

@@ -0,0 +1 @@
+{"        ": 50280, "    ": 50284, "                          ": 50262, "                      ": 50266, "\t\t\t\t\t\t\t": 50289, "                        ": 50264, "         ": 50279, "       ": 50281, "\t\t\t\t\t\t\t\t\t": 50287, "  ": 50286, "\t\t\t": 50293, "                           ": 50261, "      ": 50282, "     ": 50283, "                   ": 50269, "               ": 50273, "                 ": 50271, "\t\t\t\t\t\t\t\t": 50288, "   ": 50285, "            ": 50276, "\t\t\t\t\t\t": 50290, "\t\t\t\t\t": 50291, "                         ": 50263, "          ": 50278, "                              ": 50258, "                  ": 50270, "                             ": 50259, "                ": 50272, "              ": 50274, "                     ": 50267, "                    ": 50268, "\t\t": 50294, "                               ": 50257, "           ": 50277, "\t\t\t\t": 50292, "                            ": 50260, "                       ": 50265, "             ": 50275}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "codegen-16B-multi",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 6144,
+  "n_head": 24,
+  "n_inner": null,
+  "n_layer": 34,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1e+20, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "CodeGenTokenizer"}