Change use_cache to true

This speeds up how quickly text is outputted by the model

config.json

@@ -1,23 +1,28 @@
 {
-  "_name_or_path": "/workspace/victor123_WizardLM",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "LlamaForCausalLM"
+    "OPTForCausalLM"
   ],
-  "bos_token_id": 1,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
   "eos_token_id": 2,
-  "hidden_act": "silu",
+  "ffn_dim": 16384,
   "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
   "max_position_embeddings": 2048,
-  "model_type": "llama",
+  "model_type": "opt",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
-  "use_cache": false,
-  "vocab_size": 32001
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 4096
 }