添加0613模型的声明

openai对gpt-3.5-turbo的RPM限制是3，而gpt-3.5-turbo-0613的RPM是60，虽然两个模型的内容是一致的，但是选定特定模型可以获得更高的RPM和TPM

config.py

@@ -46,7 +46,7 @@
 
 # 模型选择是 (注意: LLM_MODEL是默认选中的模型, 同时它必须被包含在AVAIL_LLM_MODELS切换列表中 )
 LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"]
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0613", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"]
 # P.S. 其他可用的模型还包括 ["newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU

request_llm/bridge_all.py

@@ -93,6 +93,24 @@ def decode(self, *args, **kwargs):
         "token_cnt": get_token_num_gpt35,
     },
 
+    "gpt-3.5-turbo-0613": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 4096,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+    "gpt-3.5-turbo-16k-0613": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 1024 * 16,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
     "gpt-4": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,