@lobehub/chat 1.55.2 → 1.55.4

package/CHANGELOG.md

@@ -2,6 +2,56 @@
 
 # Changelog
 
+### [Version 1.55.4](https://github.com/lobehub/lobe-chat/compare/v1.55.3...v1.55.4)
+
+<sup>Released on **2025-02-15**</sup>
+
+#### 💄 Styles
+
+- **misc**: Improve mobile params style.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Improve mobile params style, closes [#6176](https://github.com/lobehub/lobe-chat/issues/6176) ([b5276de](https://github.com/lobehub/lobe-chat/commit/b5276de))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.55.3](https://github.com/lobehub/lobe-chat/compare/v1.55.2...v1.55.3)
+
+<sup>Released on **2025-02-15**</sup>
+
+#### 💄 Styles
+
+- **misc**: Add deepseek r1 distill models for qwen series.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Add deepseek r1 distill models for qwen series, closes [#5850](https://github.com/lobehub/lobe-chat/issues/5850) ([4a96a05](https://github.com/lobehub/lobe-chat/commit/4a96a05))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.55.2](https://github.com/lobehub/lobe-chat/compare/v1.55.1...v1.55.2)
 
 <sup>Released on **2025-02-15**</sup>

package/changelog/v1.json

@@ -1,4 +1,22 @@
 [
+  {
+    "children": {
+      "improvements": [
+        "Improve mobile params style."
+      ]
+    },
+    "date": "2025-02-15",
+    "version": "1.55.4"
+  },
+  {
+    "children": {
+      "improvements": [
+        "Add deepseek r1 distill models for qwen series."
+      ]
+    },
+    "date": "2025-02-15",
+    "version": "1.55.3"
+  },
   {
     "children": {
       "fixes": [

package/docs/self-hosting/server-database/docker-compose.mdx

@@ -315,8 +315,7 @@ The script supports the following deployment modes; please choose the appropriat
 
 ## Custom Deployment
 
-This section mainly introduces the configurations that need to be modified to customize the deployment of the LobeChat service in different network environments.
-Before starting, you can download the [Docker Compose configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml) and the [environment variable configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/.env.en_US.example).
+This section mainly introduces the configurations that need to be modified to customize the deployment of the LobeChat service in different network environments. Before starting, you can download the [Docker Compose configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml) and the [environment variable configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/refs/heads/main/docker-compose/local/.env.example).
 
 ```sh
 curl -O https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml
@@ -696,7 +695,6 @@ MINIO_ROOT_PASSWORD=Crj1570768
 MINIO_LOBE_BUCKET=lobe
 S3_ACCESS_KEY_ID=dB6Uq9CYZPdWSZouPyEd
 S3_SECRET_ACCESS_KEY=aPBW8CVULkh8bw1GatlT0GjLihcXHLNwRml4pieS
-
 ```
 
 - `docker-compose.yml`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.55.2",
+  "version": "1.55.4",
   "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",
@@ -126,13 +126,13 @@
     "@lobehub/chat-plugins-gateway": "^1.9.0",
     "@lobehub/icons": "^1.69.0",
     "@lobehub/tts": "^1.28.0",
-    "@lobehub/ui": "^1.164.10",
+    "@lobehub/ui": "^1.164.15",
     "@neondatabase/serverless": "^0.10.4",
     "@next/third-parties": "^15.1.4",
     "@react-spring/web": "^9.7.5",
     "@sentry/nextjs": "^7.120.2",
     "@serwist/next": "^9.0.11",
-    "@t3-oss/env-nextjs": "^0.11.1",
+    "@t3-oss/env-nextjs": "^0.12.0",
     "@tanstack/react-query": "^5.62.16",
     "@trpc/client": "next",
     "@trpc/next": "next",

package/src/config/aiModels/qwen.ts

@@ -376,7 +376,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 131_072,
-    description: 
+    description:
       '指令跟随、数学、解题、代码整体提升，万物识别能力提升，支持多样格式直接精准定位视觉元素，支持对长视频文件（最长10分钟）进行理解和秒级别的事件时刻定位，能理解时间先后和快慢，基于解析和定位能力支持操控OS或Mobile的Agent，关键信息抽取能力和Json格式输出能力强，此版本为72B版本，本系列能力最强的版本。',
     displayName: 'Qwen2.5 VL 72B',
     id: 'qwen2.5-vl-72b-instruct',
@@ -394,7 +394,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 131_072,
-    description: 
+    description:
       '指令跟随、数学、解题、代码整体提升，万物识别能力提升，支持多样格式直接精准定位视觉元素，支持对长视频文件（最长10分钟）进行理解和秒级别的事件时刻定位，能理解时间先后和快慢，基于解析和定位能力支持操控OS或Mobile的Agent，关键信息抽取能力和Json格式输出能力强，此版本为72B版本，本系列能力最强的版本。',
     displayName: 'Qwen2.5 VL 7B',
     id: 'qwen2.5-vl-7b-instruct',
@@ -412,8 +412,8 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 131_072,
-    description: 
-      'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力，尤其在数学、代码、自然语言推理等任务上。',
+    description:
+      'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力。在数学、代码、自然语言推理等任务上，性能较高，能力较强。',
     displayName: 'DeepSeek R1',
     enabled: true,
     id: 'deepseek-r1',
@@ -431,7 +431,7 @@ const qwenChatModels: AIChatModelCard[] = [
       functionCall: true,
     },
     contextWindowTokens: 131_072,
-    description: 
+    description:
       'DeepSeek-V3 为自研 MoE 模型，671B 参数，激活 37B，在 14.8T token 上进行了预训练，在长文本、代码、数学、百科、中文能力上表现优秀。',
     displayName: 'DeepSeek V3',
     enabled: true,
@@ -450,8 +450,8 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 131_072,
-    description: 
-      'DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。',
+    description:
+      'DeepSeek-R1-Distill-Qwen-1.5B 是一个基于 Qwen2.5-Math-1.5B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
     displayName: 'DeepSeek R1 Distill Qwen 1.5B',
     id: 'deepseek-r1-distill-qwen-1.5b',
     maxOutput: 8192,
@@ -467,7 +467,7 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
+    description: "DeepSeek-R1-Distill-Qwen-7B 是一个基于 Qwen2.5-Math-7B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
     displayName: "DeepSeek R1 Distill Qwen 7B",
     id: "deepseek-r1-distill-qwen-7b",
     maxOutput: 8192,
@@ -483,9 +483,9 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
-    displayName: "DeepSeek R1 Distill Llama 8B",
-    id: "deepseek-r1-distill-llama-8b",
+    description: "DeepSeek-R1-Distill-Qwen-14B 是一个基于 Qwen2.5-14B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
+    displayName: "DeepSeek R1 Distill Qwen 14B",
+    id: "deepseek-r1-distill-qwen-14b",
     maxOutput: 8192,
     pricing: {
       currency: "CNY",
@@ -499,9 +499,9 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
-    displayName: "DeepSeek R1 Distill Qwen 14B",
-    id: "deepseek-r1-distill-qwen-14b",
+    description: "DeepSeek-R1-Distill-Qwen-32B 是一个基于 Qwen2.5-32B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
+    displayName: "DeepSeek R1 Distill Qwen 32B",
+    id: "deepseek-r1-distill-qwen-32b",
     maxOutput: 8192,
     pricing: {
       currency: "CNY",
@@ -515,9 +515,9 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
-    displayName: "DeepSeek R1 Distill Qwen 32B",
-    id: "deepseek-r1-distill-qwen-32b",
+    description: "DeepSeek-R1-Distill-Llama-8B 是一个基于 Llama-3.1-8B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
+    displayName: "DeepSeek R1 Distill Llama 8B",
+    id: "deepseek-r1-distill-llama-8b",
     maxOutput: 8192,
     pricing: {
       currency: "CNY",
@@ -531,7 +531,7 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
+    description: "DeepSeek-R1-Distill-Llama-70B 是一个基于 Llama-3.3-70B-Instruct 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
     displayName: "DeepSeek R1 Distill Llama 70B",
     id: "deepseek-r1-distill-llama-70b",
     maxOutput: 8192,

package/src/config/modelProviders/qwen.ts

@@ -294,7 +294,7 @@ const Qwen: ModelProviderCard = {
     },
     {
       contextWindowTokens: 128_000,
-      description: 
+      description:
         '指令跟随、数学、解题、代码整体提升，万物识别能力提升，支持多样格式直接精准定位视觉元素，支持对长视频文件（最长10分钟）进行理解和秒级别的事件时刻定位，能理解时间先后和快慢，基于解析和定位能力支持操控OS或Mobile的Agent，关键信息抽取能力和Json格式输出能力强，此版本为72B版本，本系列能力最强的版本。',
       displayName: 'Qwen2.5 VL 72B',
       id: 'qwen2.5-vl-72b-instruct',
@@ -307,9 +307,9 @@ const Qwen: ModelProviderCard = {
       vision: true,
     },
     {
-      contextWindowTokens: 65_536,
-      description: 
-        'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力，尤其在数学、代码、自然语言推理等任务上。',
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力。在数学、代码、自然语言推理等任务上，性能较高，能力较强。',
       displayName: 'DeepSeek R1',
       id: 'deepseek-r1',
       pricing: {
@@ -320,8 +320,8 @@ const Qwen: ModelProviderCard = {
       releasedAt: '2025-01-27',
     },
     {
-      contextWindowTokens: 65_536,
-      description: 
+      contextWindowTokens: 131_072,
+      description:
         'DeepSeek-V3 为自研 MoE 模型，671B 参数，激活 37B，在 14.8T token 上进行了预训练，在长文本、代码、数学、百科、中文能力上表现优秀。',
       displayName: 'DeepSeek V3',
       id: 'deepseek-v3',
@@ -332,6 +332,84 @@ const Qwen: ModelProviderCard = {
       },
       releasedAt: '2025-01-27',
     },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-1.5B 是一个基于 Qwen2.5-Math-1.5B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 1.5B',
+      id: 'deepseek-r1-distill-qwen-1.5b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-7B 是一个基于 Qwen2.5-Math-7B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 7B',
+      id: 'deepseek-r1-distill-qwen-7b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-14B 是一个基于 Qwen2.5-14B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 14B',
+      id: 'deepseek-r1-distill-qwen-14b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-32B 是一个基于 Qwen2.5-32B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 32B',
+      id: 'deepseek-r1-distill-qwen-32b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Llama-8B 是一个基于 Llama-3.1-8B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Llama 8B',
+      id: 'deepseek-r1-distill-llama-8b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Llama-70B 是一个基于 Llama-3.3-70B-Instruct 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Llama 70B',
+      id: 'deepseek-r1-distill-llama-70b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
   ],
   checkModel: 'qwen-turbo-latest',
   description:

package/src/features/ChatInput/ActionBar/Params/ParamsControls.tsx

@@ -1,5 +1,6 @@
 import { Form, Tag } from '@lobehub/ui';
 import type { FormItemProps } from '@lobehub/ui/es/Form/components/FormItem';
+import { createStyles } from 'antd-style';
 import isEqual from 'fast-deep-equal';
 import { debounce } from 'lodash-es';
 import { memo } from 'react';
@@ -16,10 +17,20 @@ import {
 import { useAgentStore } from '@/store/agent';
 import { agentSelectors } from '@/store/agent/selectors';
 
+const useStyles = createStyles(({ css }) => ({
+  container: css`
+    .ant-form-group {
+      padding-inline: 0;
+      background: transparent;
+    }
+  `,
+}));
+
 interface ParamsControlsProps {
   setUpdating: (updating: boolean) => void;
 }
 const ParamsControls = memo<ParamsControlsProps>(({ setUpdating }) => {
+  const { styles } = useStyles();
   const { t } = useTranslation('setting');
 
   const updateAgentConfig = useAgentStore((s) => s.updateAgentConfig);
@@ -75,13 +86,13 @@ const ParamsControls = memo<ParamsControlsProps>(({ setUpdating }) => {
 
   return (
     <Form
+      className={styles.container}
       initialValues={config}
       itemMinWidth={200}
       items={items}
       itemsType={'flat'}
       onValuesChange={debounce(async (values) => {
         setUpdating(true);
-        console.log(values);
         await updateAgentConfig(values);
         setUpdating(false);
       }, 500)}

package/src/features/ChatInput/ActionBar/Params/index.tsx

@@ -7,6 +7,7 @@ import { useTranslation } from 'react-i18next';
 import { Flexbox } from 'react-layout-kit';
 
 import UpdateLoading from '@/components/Loading/UpdateLoading';
+import { useIsMobile } from '@/hooks/useIsMobile';
 
 import ParamsControls from './ParamsControls';
 
@@ -16,6 +17,7 @@ const Params = memo(() => {
   const [isUpdating, setUpdating] = useState(false);
 
   const theme = useTheme();
+  const isMobile = useIsMobile();
   return (
     <Popover
       arrow={false}
@@ -24,7 +26,10 @@ const Params = memo(() => {
       open={popoverOpen}
       placement={'top'}
       styles={{
-        body: { minWidth: 400 },
+        body: {
+          minWidth: isMobile ? undefined : 400,
+          width: isMobile ? '100vw' : undefined,
+        },
       }}
       title={
         <Flexbox horizontal justify={'space-between'}>