Added instruct tokens and config fix

config.json

@@ -1,8 +1,4 @@
 {
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPTNeoXForCausalLM"
-  ],
   "attn_pdrop": 0.0,
   "pad_token_id": 0,
   "unk_token_id": 1,
@@ -10,31 +6,7 @@
   "sep_token_id": 3,
   "eos_token_id": 4,
   "embd_pdrop": 0.0,
-  "gradient_checkpointing": false,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gptj",
-  "model_dtype": "fp16",
-  "n_embd": 4096,
-  "n_head": 16,
-  "n_layer": 32,
-  "n_positions": 2048,
-  "rotary": true,
-  "rotary_dim": 64,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
   "transformers_version": "4.10.0.dev0",
   "tokenizer_class": "T5Tokenizer",
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "temperature": 1.0,
-      "max_length": 50
-    }
-  },
-  "use_cache": true,
-  "vocab_size": 52000
+  "vocab_size": 52100
 }

tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sep_token": "<sep>", "cls_token": "<cls>"}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sep_token": "<sep>", "cls_token": "<cls>", "tokenizer_class": "T5Tokenizer"}