更新模型

modules/presets.py

@@ -45,45 +45,20 @@ INDEX_QUERY_TEMPRATURE = 1.0
 CHUANHU_TITLE = i18n("川虎Chat 🚀")
 
 CHUANHU_DESCRIPTION = i18n(
-    "由Bilibili [土川虎虎虎](https://space.bilibili.com/29125536)、[明昭MZhao](https://space.bilibili.com/24807452) 和 [Keldos](https://github.com/Keldos-Li) 开发<br />访问川虎Chat的 [GitHub项目](https://github.com/GaiZhenbiao/ChuanhuChatGPT) 下载最新版脚本")
+    "由Bilibili [土川虎虎虎](https://space.bilibili.com/29125536)、[明昭MZhao](https://space.bilibili.com/24807452) 和 [Keldos](https://github.com/Keldos-Li) 开发<br />访问川虎Chat的 [GitHub项目](https://github.com/GaiZhenbiao/ChuanhuChatGPT) 下载最新版脚本"
+)
 
 ONLINE_MODELS = [
-    "gpt-3.5-turbo-1106",
-    "gpt-4-1106-preview",
+    "gpt-4-turbo",
     "gpt-3.5-turbo",
-    "gpt-3.5-turbo-16k",
-    "gpt-3.5-turbo-0301",
-    "gpt-3.5-turbo-0613",
-    "gpt-4",
-    "gpt-4-0314",
-    "gpt-4-0613",
-    "gpt-4-32k",
-    "gpt-4-32k-0314",
-    "gpt-4-32k-0613",
-    "川虎助理",
-    "川虎助理 Pro",
-    "xmchat",
-    "yuanai-1.0-base_10B",
-    "yuanai-1.0-translate",
-    "yuanai-1.0-dialog",
-    "yuanai-1.0-rhythm_poems",
-    "minimax-abab4-chat",
-    "minimax-abab5-chat",
+    "gpt-4-turbo-2024-04-09",
+    "gpt-4-1106-preview",
+    "gpt-4-0125-preview",
 ]
 
-LOCAL_MODELS = [
-    "chatglm-6b",
-    "chatglm-6b-int4",
-    "chatglm-6b-int4-qe",
-    "StableLM",
-    "MOSS",
-    "llama-7b-hf",
-    "llama-13b-hf",
-    "llama-30b-hf",
-    "llama-65b-hf",
-]
+LOCAL_MODELS = ["chatglm-6b"]
 
-if os.environ.get('HIDE_LOCAL_MODELS', 'false') == 'true':
+if os.environ.get("HIDE_LOCAL_MODELS", "false") == "true":
     MODELS = ONLINE_MODELS
 else:
     MODELS = ONLINE_MODELS + LOCAL_MODELS
@@ -110,7 +85,12 @@ MODEL_TOKEN_LIMIT = {
     "gpt-4-0613": 8192,
     "gpt-4-32k": 32768,
     "gpt-4-32k-0314": 32768,
-    "gpt-4-32k-0613": 32768
+    "gpt-4-32k-0613": 32768,
+    "gpt-4-turbo": 128000,
+    "gpt-3.5-turbo": 16385,
+    "gpt-4-turbo-2024-04-09": 128000,
+    "gpt-4-1106-preview": 128000,
+    "gpt-4-0125-preview": 128000,
 }
 
 TOKEN_OFFSET = 1000  # 模型的token上限减去这个值，得到软上限。到达软上限之后，自动尝试减少token占用。
@@ -119,13 +99,8 @@ REDUCE_TOKEN_FACTOR = 0.5  # 与模型token上限想乘，得到目标token数
 
 REPLY_LANGUAGES = [
     "简体中文",
-    "繁體中文",
     "English",
-    "日本語",
-    "Español",
-    "Français",
-    "Deutsch",
-    "跟随问题语言（不稳定）"
+    "跟随问题语言（不稳定）",
 ]
 
 WEBSEARCH_PTOMPT_TEMPLATE = """\