revise config

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/group/40005/chengyuewu/open-instruct/output/llama-7b-add-8-3e-4-continue-ft-stack-python",
+  "_name_or_path": "TencentARC/LLaMA_Pro",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,15 +9,13 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 16384,
-  "max_sequence_length": 16384,
+  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,

generation_config.json

@@ -1,7 +1,10 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
+  "max_length": 4096,
   "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.33.3"
 }

special_tokens_map.json

@@ -2,14 +2,14 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -17,7 +17,7 @@
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -5,7 +5,7 @@
     "__type": "AddedToken",
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -14,13 +14,14 @@
     "__type": "AddedToken",
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "legacy": true,
-  "model_max_length": 2048,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
@@ -28,7 +29,7 @@
     "__type": "AddedToken",
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },