Update llama-java libs

eoctet · Jan 5, 2024 · e56d675 · e56d675
1 parent 5542f77
commit e56d675
Show file tree

Hide file tree

Showing 7 changed files with 15 additions and 14 deletions.
diff --git a/README.Zh_CN.md b/README.Zh_CN.md
@@ -11,7 +11,7 @@
 
 #### 提供
 - 简单易用的Java库 `llama-java-core`
-- 完整的API服务 `llama-java-app` 用于私有服务
+- 完整的API服务 `llama-java-app`
   - `服务端部署`，快速实现私有化服务
   - `命令行交互`，简单的本地聊天交互
 
@@ -65,7 +65,7 @@ bash app_server.sh start
 >
 > > 完整的API信息请参考[`API 文档`](docs/API.md)。
 
-![webui.png](docs%2Fwebui.png)
+![webui.png](docs/webui.png)
 
 举个栗子
 
@@ -285,7 +285,7 @@ public class ContinuousChatExample {
 
 **chat.octet.model.components.processor.LogitsProcessor**
 
-自定义一个处理器对词的概率分布进行调整，控制模型推理的生成结果。这里是一个示例：[NoBadWordsLogitsProcessor.java](src%2Fmain%2Fjava%2Fchat%2Foctet%2Fmodel%2Fcomponents%2Fprocessor%2Fimpl%2FNoBadWordsLogitsProcessor.java)
+自定义一个处理器对词的概率分布进行调整，控制模型推理的生成结果。这里是一个示例：[NoBadWordsLogitsProcessor.java](llama-java-core/src/main/java/chat/octet/model/components/processor/impl/NoBadWordsLogitsProcessor.java)
 
 ```java
     Map<Integer, String> logitBias = Maps.newLinkedHashMap();
@@ -300,7 +300,7 @@ public class ContinuousChatExample {
 
 **chat.octet.model.components.criteria.StoppingCriteria**
 
-自定义一个控制器实现对模型推理的停止规则控制，例如：控制生成最大超时时间，这里是一个示例：[MaxTimeCriteria](src%2Fmain%2Fjava%2Fchat%2Foctet%2Fmodel%2Fcomponents%2Fcriteria%2Fimpl%2FMaxTimeCriteria.java)
+自定义一个控制器实现对模型推理的停止规则控制，例如：控制生成最大超时时间，这里是一个示例：[MaxTimeCriteria](llama-java-core/src/main/java/chat/octet/model/components/criteria/impl/MaxTimeCriteria.java)
 
 ```java
     long maxTime = TimeUnit.MINUTES.toMillis(Optional.ofNullable(params.getTimeout()).orElse(10L));
@@ -311,7 +311,7 @@ public class ContinuousChatExample {
             .build();
 ```
 
-> 完整的文档请参考 [Java docs](docs%2Fapidocs%2Findex.html)
+> 完整的文档请参考 `Java docs`
 
 #### 如何编译
 

diff --git a/README.md b/README.md
@@ -11,7 +11,7 @@ This is a 🦙 `LLaMA` Java project. You can use it to deploy your own private s
 
 #### Provides
 - Simple Java library `llama-java-core`
-- Complete API services `llama-java-app` for private services
+- Complete API services `llama-java-app`
   - `Server deployment` to quickly realize privatized services
   - `CLI Interaction`, simple local chat interaction
 
@@ -65,7 +65,7 @@ Following the interface specifications of `ChatGPT`, only the main interfaces ar
 >
 > > More information: [`API Docs`](docs/API.md).
 
-![webui.png](docs%2Fwebui.png)
+![webui.png](docs/webui.png)
 
 For example
 
@@ -285,7 +285,7 @@ You can use `LogitsProcessor` and `StoppingCriteria` to customize and control th
 
 **chat.octet.model.components.processor.LogitsProcessor**
 
-Customize a processor to adjust the probability distribution of words and control the generation of model inference results. Here is an example: [NoBadWordsLogitsProcessor.java](src%2Fmain%2Fjava%2Fchat%2Foctet%2Fmodel%2Fcomponents%2Fprocessor%2Fimpl%2FNoBadWordsLogitsProcessor.java)
+Customize a processor to adjust the probability distribution of words and control the generation of model inference results. Here is an example: [NoBadWordsLogitsProcessor.java](llama-java-core/src/main/java/chat/octet/model/components/processor/impl/NoBadWordsLogitsProcessor.java)
 
 ```java
     Map<Integer, String> logitBias = Maps.newLinkedHashMap();
@@ -300,7 +300,7 @@ Customize a processor to adjust the probability distribution of words and contro
 
 **chat.octet.model.components.criteria.StoppingCriteria**
 
-Customize a controller to implement stop rule control for model inference, such as controlling the maximum timeout time generated. Here is an example: [MaxTimeCriteria](src%2Fmain%2Fjava%2Fchat%2Foctet%2Fmodel%2Fcomponents%2Fcriteria%2Fimpl%2FMaxTimeCriteria.java)
+Customize a controller to implement stop rule control for model inference, such as controlling the maximum timeout time generated. Here is an example: [MaxTimeCriteria](llama-java-core/src/main/java/chat/octet/model/components/criteria/impl/MaxTimeCriteria.java)
 
 ```java
     long maxTime = TimeUnit.MINUTES.toMillis(Optional.ofNullable(params.getTimeout()).orElse(10L));
@@ -311,7 +311,7 @@ Customize a controller to implement stop rule control for model inference, such
             .build();
 ```
 
-> More information: [Java docs](docs%2Fapidocs%2Findex.html)
+> More information: `Java docs`
 
 #### Build
 

diff --git a/llama-java-app/docs/API.md → docs/API.md b/llama-java-app/docs/API.md → docs/API.md
diff --git a/llama-java-app/docs/webui.png → docs/webui.png b/llama-java-app/docs/webui.png → docs/webui.png
diff --git a/llama-java-app/pom.xml b/llama-java-app/pom.xml
@@ -6,7 +6,7 @@
     <parent>
         <groupId>chat.octet</groupId>
         <artifactId>llama-java</artifactId>
-        <version>1.3.2</version>
+        <version>1.3.3</version>
     </parent>
 
     <artifactId>llama-java-app</artifactId>
@@ -43,6 +43,7 @@
         <lombok.version>1.18.26</lombok.version>
         <guava.version>32.1.2-jre</guava.version>
         <spring-boot.version>2.7.16</spring-boot.version>
+        <llama.java.version>1.3.3</llama.java.version>
     </properties>
 
     <dependencies>
@@ -114,7 +115,7 @@
         <dependency>
             <groupId>chat.octet</groupId>
             <artifactId>llama-java-core</artifactId>
-            <version>1.3.2</version>
+            <version>${llama.java.version}</version>
         </dependency>
         <dependency>
             <groupId>org.yaml</groupId>

diff --git a/llama-java-core/pom.xml b/llama-java-core/pom.xml
@@ -6,7 +6,7 @@
     <parent>
         <groupId>chat.octet</groupId>
         <artifactId>llama-java</artifactId>
-        <version>1.3.2</version>
+        <version>1.3.3</version>
     </parent>
 
     <artifactId>llama-java-core</artifactId>

diff --git a/pom.xml b/pom.xml
@@ -7,7 +7,7 @@
     <groupId>chat.octet</groupId>
     <artifactId>llama-java</artifactId>
     <packaging>pom</packaging>
-    <version>1.3.2</version>
+    <version>1.3.3</version>
 
     <modules>
         <module>llama-java-core</module>