Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: max_tokens of qwen-plus & qwen-plus-chat #5480

Conversation

crazywoola
Copy link
Member

Description

Update the wrong settings of max_tokens

Type of Change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)

Suggested Checklist:

  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • My changes generate no new warnings
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

@crazywoola crazywoola requested a review from takatost June 21, 2024 07:45
@crazywoola crazywoola marked this pull request as ready for review June 21, 2024 07:45
@dosubot dosubot bot added size:XS This PR changes 0-9 lines, ignoring generated files. 🐞 bug Something isn't working labels Jun 21, 2024
@crazywoola crazywoola requested a review from laipz8200 June 21, 2024 08:27
@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Jun 21, 2024
@crazywoola crazywoola merged commit 91d38a5 into main Jun 21, 2024
16 checks passed
@crazywoola crazywoola deleted the 5462-the-official-max_tokens-for-the-qwen-plus-chat-model-is-2000-but-the-system-can-only-set-a-maximum-of-1500 branch June 21, 2024 08:49
XiaoLey pushed a commit to XiaoLey/dify that referenced this pull request Jun 22, 2024
ZhouhaoJiang added a commit that referenced this pull request Jun 24, 2024
* refs/heads/deploy/dev: (273 commits)
  chore: host required
  fix: monitor copywrite
  feat: make show citations enable default
  chore: use singular style in middleware config class name (#5502)
  refactor: extract hosted service configs into dify config (#5504)
  fix: summary of duckduckgo_search (#5488)
  fix: zhipu tool calling, this PR fixes the bug described in issue #5496 (#5469)
  fix: tongyi json output (#5396)
  fix: firecrawl apikey not start with fc- (#5498)
  fix lock
  refactor: extract db configs and celery configs into dify config (#5491)
  refactor: extract storage provider configs into dify configs (#5443)
  chore: use singular style in config class name (#5489)
  chore: remove pip support for api service (#5453)
  Add Oracle23ai as a vector datasource (#5342)
  build: support Poetry for depencencies tool in api's Dockerfile (#5105)
  feat: add ops trace encrypt_config decrypt_config obfuscate_config
  feat: add remove tracing app
  fix: max_tokens of qwen-plus & qwen-plus-chat (#5480)
  feat: add support for Vertex AI claude-3-5-sonnet@20240620 (#5475)
  ...
HuberyHuV1 pushed a commit to HuberyHuV1/dify that referenced this pull request Jul 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🐞 bug Something isn't working lgtm This PR has been approved by a maintainer size:XS This PR changes 0-9 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

The official max_tokens for the qwen-plus-chat model is 2000, but the system can only set a maximum of 1500
2 participants