AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-17 03:55:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update and fix the model param of Deepseek (#5329)

Browse Source
This commit is contained in:
Richards Tu 2024-06-17 21:40:04 +08:00 committed by GitHub
parent 7305713b97
commit c163521b9e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
api/core/model_runtime/model_providers/deepseek/llm/deepseek-chat.yaml
View File

@ -23,7 +23,7 @@ parameter_rules:
type: int type: int
default: 4096 default: 4096
min: 1 min: 1
max: 32000 max: 4096
help: help:
zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。 zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter. en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.

4
api/core/model_runtime/model_providers/deepseek/llm/deepseek-coder.yaml
View File

@ -7,7 +7,7 @@ features:
- agent-thought - agent-thought
model_properties: model_properties:
mode: chat mode: chat
context_size: 16000 context_size: 32000
parameter_rules: parameter_rules:
- name: temperature - name: temperature
use_template: temperature use_template: temperature
@ -22,5 +22,5 @@ parameter_rules:
- name: max_tokens - name: max_tokens
use_template: max_tokens use_template: max_tokens
min: 1 min: 1
max: 32000 max: 4096
default: 1024 default: 1024