AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-06-30 06:45:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Updata tongyi models (#9552)

Browse Source
This commit is contained in:
AAEE86 2024-10-21 19:04:45 +08:00 committed by GitHub
parent 37fea072bc
commit 9b32bfb3db
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
View File

@ -76,3 +76,4 @@ pricing:
output: '0.12' output: '0.12'
unit: '0.001' unit: '0.001'
currency: RMB currency: RMB
deprecated: true

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
View File

@ -10,7 +10,7 @@ features:
- stream-tool-call - stream-tool-call
model_properties: model_properties:
mode: chat mode: chat
context_size: 8000 context_size: 32000
parameter_rules: parameter_rules:
- name: temperature - name: temperature
use_template: temperature use_template: temperature
@ -26,7 +26,7 @@ parameter_rules:
type: int type: int
default: 2000 default: 2000
min: 1 min: 1
max: 2000 max: 8192
help: 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。 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. 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.

2
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
View File

@ -10,7 +10,7 @@ features:
- stream-tool-call - stream-tool-call
model_properties: model_properties:
mode: chat mode: chat
context_size: 131072 context_size: 128000
parameter_rules: parameter_rules:
- name: temperature - name: temperature
use_template: temperature use_template: temperature

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
View File

@ -10,7 +10,7 @@ features:
- stream-tool-call - stream-tool-call
model_properties: model_properties:
mode: chat mode: chat
context_size: 8000 context_size: 128000
parameter_rules: parameter_rules:
- name: temperature - name: temperature
use_template: temperature use_template: temperature
@ -26,7 +26,7 @@ parameter_rules:
type: int type: int
default: 2000 default: 2000
min: 1 min: 1
max: 2000 max: 8192
help: 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。 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. 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.