Update config.json

config.json

@@ -22,5 +22,13 @@
     "transformers_version": "4.31.0.dev0",
     "use_cache": true,
     "vocab_size": 32000,
-    "pad_token_id": 0
+    "pad_token_id": 0,
+    "quantization_config": {
+        "quant_method": "awq",
+        "zero_point": true,
+        "group_size": 128,
+        "bits": 4,
+        "version": "gemm",
+        "backend": "autoawq"
+    }
 }

tokenizer_config.json

@@ -18,6 +18,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,