初始化项目，由ModelHub XC社区提供模型

Model: TheBloke/vietnamese-llama2-7B-40GB-GPTQ
Source: Original Platform

generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "max_memory": {
+    "cpu": 329543315456
+  },
+  "no_split_module_classes": [
+    "LlamaDecoderLayer"
+  ],
+  "pad_token_id": 0,
+  "special_dtypes": {},
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.31.0"
+}