Spaces:
Running
Running
LXR520
Chuan Hu
commited on
修改了README.md的支持模型列表, 修改了config_example.json里关于Google PaLM API描述不当的问题 (#1113)
Browse files* Update config_example.json
* Update config_example.json
* Add files via upload
* Add files via upload
* Update config_example.json
* Add files via upload
* Add files via upload
* Update config_example.json
* add ChatGLM3
* Update config_example.json
修改注释用户列表错误的地方
---------
Co-authored-by: Chuan Hu <[email protected]>
- README.md +10 -10
- config_example.json +2 -2
- readme/README_en.md +10 -10
- readme/README_ja.md +9 -9
- readme/README_ru.md +9 -9
README.md
CHANGED
@@ -66,16 +66,16 @@
|
|
66 |
|
67 |
| API 调用模型 | 备注 | 本地部署模型 | 备注 |
|
68 |
| :---: | --- | :---: | --- |
|
69 |
-
| [ChatGPT(GPT-4)](https://chat.openai.com) | 支持微调 gpt-3.5 | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B))
|
70 |
-
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | 支持 Lora 模型
|
71 |
-
| [Google
|
72 |
-
| [讯飞星火认知大模型](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS)
|
73 |
-
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [通义千问](https://github.com/QwenLM/Qwen/tree/main)
|
74 |
-
| [MiniMax](https://api.minimax.chat/)
|
75 |
-
| [XMChat](https://github.com/MILVLG/xmchat) |
|
76 |
-
| [Midjourney](https://www.midjourney.com/) |
|
77 |
-
| [Claude](https://www.anthropic.com/) | ✨ 现已支持Claude 3 Opus、Sonnet,Haiku
|
78 |
-
| DALL·E 3
|
79 |
|
80 |
## 使用技巧
|
81 |
|
|
|
66 |
|
67 |
| API 调用模型 | 备注 | 本地部署模型 | 备注 |
|
68 |
| :---: | --- | :---: | --- |
|
69 |
+
| [ChatGPT(GPT-4)](https://chat.openai.com) | 支持微调 gpt-3.5 | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)) ([ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b)) ||
|
70 |
+
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | 支持 Lora 模型 |
|
71 |
+
| [Google Gemini Pro](https://ai.google.dev/gemini-api/docs/api-key?hl=zh-cn) | | [StableLM](https://github.com/Stability-AI/StableLM) ||
|
72 |
+
| [讯飞星火认知大模型](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS) ||
|
73 |
+
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [通义千问](https://github.com/QwenLM/Qwen/tree/main) ||
|
74 |
+
| [MiniMax](https://api.minimax.chat/) ||||
|
75 |
+
| [XMChat](https://github.com/MILVLG/xmchat) | 不支持流式传输|||
|
76 |
+
| [Midjourney](https://www.midjourney.com/) | 不支持流式传输|||
|
77 |
+
| [Claude](https://www.anthropic.com/) | ✨ 现已支持Claude 3 Opus、Sonnet,Haiku将会在推出后的第一时间支持|||
|
78 |
+
| DALL·E 3 ||||
|
79 |
|
80 |
## 使用技巧
|
81 |
|
config_example.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
|
4 |
//== API 配置 ==
|
5 |
"openai_api_key": "", // 你的 OpenAI API Key,一般必填,若空缺则需在图形界面中填入API Key
|
6 |
-
"google_genai_api_key": "", // 你的 Google
|
7 |
"xmchat_api_key": "", // 你的 xmchat API Key,用于 XMChat 对话模型
|
8 |
"minimax_api_key": "", // 你的 MiniMax API Key,用于 MiniMax 对话模型
|
9 |
"minimax_group_id": "", // 你的 MiniMax Group ID,用于 MiniMax 对话模型
|
@@ -32,7 +32,7 @@
|
|
32 |
|
33 |
//== 基础配置 ==
|
34 |
"language": "auto", // 界面语言,可选"auto", "zh_CN", "en_US", "ja_JP", "ko_KR", "sv_SE", "ru_RU", "vi_VN"
|
35 |
-
"users": [], // 用户列表,[[用户名1, 密码1], [用户名2, 密码2], ...]
|
36 |
"local_embedding": false, //是否在本地编制索引
|
37 |
"hide_history_when_not_logged_in": false, //未登录情况下是否不展示对话历史
|
38 |
"check_update": true, //是否启用检查更新
|
|
|
3 |
|
4 |
//== API 配置 ==
|
5 |
"openai_api_key": "", // 你的 OpenAI API Key,一般必填,若空缺则需在图形界面中填入API Key
|
6 |
+
"google_genai_api_key": "", // 你的 Google Gemini API Key ,用于 Google Gemini 对话模型
|
7 |
"xmchat_api_key": "", // 你的 xmchat API Key,用于 XMChat 对话模型
|
8 |
"minimax_api_key": "", // 你的 MiniMax API Key,用于 MiniMax 对话模型
|
9 |
"minimax_group_id": "", // 你的 MiniMax Group ID,用于 MiniMax 对话模型
|
|
|
32 |
|
33 |
//== 基础配置 ==
|
34 |
"language": "auto", // 界面语言,可选"auto", "zh_CN", "en_US", "ja_JP", "ko_KR", "sv_SE", "ru_RU", "vi_VN"
|
35 |
+
"users": [], // 用户列表,[["用户名1", "密码1"], ["用户名2", "密码2"], ...]
|
36 |
"local_embedding": false, //是否在本地编制索引
|
37 |
"hide_history_when_not_logged_in": false, //未登录情况下是否不展示对话历史
|
38 |
"check_update": true, //是否启用检查更新
|
readme/README_en.md
CHANGED
@@ -62,16 +62,16 @@
|
|
62 |
|
63 |
| API Callable Models | Remarks | Locally Deployed Models | Remarks |
|
64 |
| :---: | --- | :---: | --- |
|
65 |
-
| [ChatGPT(GPT-4)](https://chat.openai.com) | Support fine-tune gpt-3.5 | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B))
|
66 |
-
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | Support Lora models
|
67 |
-
| [Google
|
68 |
-
| [iFlytek Starfire Cognition Large Model](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS)
|
69 |
-
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [Qwen](https://github.com/QwenLM/Qwen/tree/main)
|
70 |
-
| [MiniMax](https://api.minimax.chat/)
|
71 |
-
| [XMChat](https://github.com/MILVLG/xmchat) | Not support streaming
|
72 |
-
| [Midjourney](https://www.midjourney.com/) | Not support streaming
|
73 |
-
| [Claude](https://www.anthropic.com/) | ✨ Now supports Claude 3 Opus and Sonnet, Haiku will be supported as soon as it is released
|
74 |
-
| DALL·E 3
|
75 |
|
76 |
## Usage Tips
|
77 |
|
|
|
62 |
|
63 |
| API Callable Models | Remarks | Locally Deployed Models | Remarks |
|
64 |
| :---: | --- | :---: | --- |
|
65 |
+
| [ChatGPT(GPT-4)](https://chat.openai.com) | Support fine-tune gpt-3.5 | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)) ([ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b)) ||
|
66 |
+
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | Support Lora models|
|
67 |
+
| [Google Gemini Pro](https://ai.google.dev/gemini-api/docs/api-key?hl=zh-cn) | | [StableLM](https://github.com/Stability-AI/StableLM)||
|
68 |
+
| [iFlytek Starfire Cognition Large Model](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS)||
|
69 |
+
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [Qwen](https://github.com/QwenLM/Qwen/tree/main)||
|
70 |
+
| [MiniMax](https://api.minimax.chat/) ||||
|
71 |
+
| [XMChat](https://github.com/MILVLG/xmchat) | Not support streaming|||
|
72 |
+
| [Midjourney](https://www.midjourney.com/) | Not support streaming|||
|
73 |
+
| [Claude](https://www.anthropic.com/) | ✨ Now supports Claude 3 Opus and Sonnet, Haiku will be supported as soon as it is released|||
|
74 |
+
| DALL·E 3 ||||
|
75 |
|
76 |
## Usage Tips
|
77 |
|
readme/README_ja.md
CHANGED
@@ -61,15 +61,15 @@
|
|
61 |
|
62 |
| API呼び出しモデル | 備考 | ローカルデプロイモデル | 備考 |
|
63 |
| :---: | --- | :---: | --- |
|
64 |
-
| [ChatGPT(GPT-4)](https://chat.openai.com) | gpt-3.5の微調整をサポート | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B))
|
65 |
-
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | Loraモデルのサポートあり
|
66 |
-
| [Google
|
67 |
-
| [讯飞星火认知大模型](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS)
|
68 |
-
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [Qwen](https://github.com/QwenLM/Qwen/tree/main)
|
69 |
-
| [MiniMax](https://api.minimax.chat/)
|
70 |
-
| [XMChat](https://github.com/MILVLG/xmchat) |
|
71 |
-
| [Midjourney](https://www.midjourney.com/) |
|
72 |
-
| [Claude](https://www.anthropic.com/)
|
73 |
|
74 |
## 使う上でのTips
|
75 |
|
|
|
61 |
|
62 |
| API呼び出しモデル | 備考 | ローカルデプロイモデル | 備考 |
|
63 |
| :---: | --- | :---: | --- |
|
64 |
+
| [ChatGPT(GPT-4)](https://chat.openai.com) | gpt-3.5の微調整をサポート | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)) ([ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b)) ||
|
65 |
+
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | Loraモデルのサポートあり |
|
66 |
+
| [Google Gemini Pro](https://ai.google.dev/gemini-api/docs/api-key?hl=zh-cn) | | [StableLM](https://github.com/Stability-AI/StableLM)||
|
67 |
+
| [讯飞星火认知大模型](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS)||
|
68 |
+
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [Qwen](https://github.com/QwenLM/Qwen/tree/main)||
|
69 |
+
| [MiniMax](https://api.minimax.chat/) ||||
|
70 |
+
| [XMChat](https://github.com/MILVLG/xmchat) | ストリーミング転送はサポートされていません|||
|
71 |
+
| [Midjourney](https://www.midjourney.com/) | ストリーミング転送はサポートされていません|||
|
72 |
+
| [Claude](https://www.anthropic.com/) ||||
|
73 |
|
74 |
## 使う上でのTips
|
75 |
|
readme/README_ru.md
CHANGED
@@ -61,15 +61,15 @@
|
|
61 |
|
62 |
| Модель с использованием API | Примечание | Локально развернутые модели | Примечание |
|
63 |
| :---: | --- | :---: | --- |
|
64 |
-
| [ChatGPT (GPT-4)](https://chat.openai.com) | Поддерживает микронастройку gpt-3.5 | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B))
|
65 |
-
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | Поддерживает модель Lora
|
66 |
-
| [Google
|
67 |
-
| [Xunfei Xinghuo Cognitive Model](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS)
|
68 |
-
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [Qwen](https://github.com/QwenLM/Qwen/tree/main)
|
69 |
-
| [MiniMax](https://api.minimax.chat/)
|
70 |
-
| [XMChat](https://github.com/MILVLG/xmchat) | Не поддерживает потоковую передачу
|
71 |
-
| [Midjourney](https://www.midjourney.com/) | Не поддерживает потоковую передачу
|
72 |
-
| [Claude](https://www.anthropic.com/)
|
73 |
|
74 |
## Советы по использованию
|
75 |
|
|
|
61 |
|
62 |
| Модель с использованием API | Примечание | Локально развернутые модели | Примечание |
|
63 |
| :---: | --- | :---: | --- |
|
64 |
+
| [ChatGPT (GPT-4)](https://chat.openai.com) | Поддерживает микронастройку gpt-3.5 | [ChatGLM](https://github.com/THUDM/ChatGLM-6B) ([ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)) ([ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b)) ||
|
65 |
+
| [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) | | [LLaMA](https://github.com/facebookresearch/llama) | Поддерживает модель Lora |
|
66 |
+
| [Google Gemini Pro](https://ai.google.dev/gemini-api/docs/api-key?hl=zh-cn) | | [StableLM](https://github.com/Stability-AI/StableLM)||
|
67 |
+
| [Xunfei Xinghuo Cognitive Model](https://xinghuo.xfyun.cn) | | [MOSS](https://github.com/OpenLMLab/MOSS)||
|
68 |
+
| [Inspur Yuan 1.0](https://air.inspur.com/home) | | [Qwen](https://github.com/QwenLM/Qwen/tree/main)||
|
69 |
+
| [MiniMax](https://api.minimax.chat/) ||||
|
70 |
+
| [XMChat](https://github.com/MILVLG/xmchat) | Не поддерживает потоковую передачу данных|||
|
71 |
+
| [Midjourney](https://www.midjourney.com/) | Не поддерживает потоковую передачу данных|||
|
72 |
+
| [Claude](https://www.anthropic.com/) ||||
|
73 |
|
74 |
## Советы по использованию
|
75 |
|