From 9b32bfb3dbdac71f214e612c7b5482549aadf3d9 Mon Sep 17 00:00:00 2001
From: AAEE86 <33052466+AAEE86@users.noreply.github.com>
Date: Mon, 21 Oct 2024 19:04:45 +0800
Subject: [PATCH] feat: Updata tongyi models (#9552)

---
 .../model_providers/tongyi/llm/qwen-max-longcontext.yaml      | 1 +
 .../model_runtime/model_providers/tongyi/llm/qwen-max.yaml    | 4 ++--
 .../model_runtime/model_providers/tongyi/llm/qwen-plus.yaml   | 2 +-
 .../model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml  | 4 ++--
 4 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
index 098494ff95..cc0bb7a117 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
@@ -76,3 +76,4 @@ pricing:
   output: '0.12'
   unit: '0.001'
   currency: RMB
+deprecated: true
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
index 9d0d3f8db3..4af4822e86 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
@@ -10,7 +10,7 @@ features:
   - stream-tool-call
 model_properties:
   mode: chat
-  context_size: 8000
+  context_size: 32000
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -26,7 +26,7 @@ parameter_rules:
     type: int
     default: 2000
     min: 1
-    max: 2000
+    max: 8192
     help:
       zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
       en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
index 9089e57255..529a29b1b5 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
@@ -10,7 +10,7 @@ features:
   - stream-tool-call
 model_properties:
   mode: chat
-  context_size: 131072
+  context_size: 128000
 parameter_rules:
   - name: temperature
     use_template: temperature
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
index 215c9ec5fc..a0c4ba6820 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
@@ -10,7 +10,7 @@ features:
   - stream-tool-call
 model_properties:
   mode: chat
-  context_size: 8000
+  context_size: 128000
 parameter_rules:
   - name: temperature
     use_template: temperature
@@ -26,7 +26,7 @@ parameter_rules:
     type: int
     default: 2000
     min: 1
-    max: 2000
+    max: 8192
     help:
       zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
       en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.