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

Added new model configurations for 'yarn-mistral' and 'deepseek-coder' #84

Merged
merged 1 commit into from
Nov 20, 2023
Merged

Added new model configurations for 'yarn-mistral' and 'deepseek-coder' #84

merged 1 commit into from
Nov 20, 2023

Conversation

Bortus-AI
Copy link
Collaborator

This commit introduces the following model configurations to the existing model registry:

  • yarn-mistral:7b-128k

    • id: yarn-mistral:7b-128k
    • maxLength: 128000 tokens
    • tokenLimit: 4096 tokens per request
    • requestLimit: 3000 requests per client
    • vendor: Ollama
  • deepseek-coder:latest

    • id: deepseek-coder:latest
    • maxLength: 16000 tokens
    • tokenLimit: 4096 tokens per request
    • requestLimit: 3000 requests per client
    • vendor: Ollama
  • deepseek-coder:6.7b

    • id: deepseek-coder:6.7b
    • maxLength: 16000 tokens
    • tokenLimit: 4096 tokens per request
    • requestLimit: 3000 requests per client
    • vendor: Ollama
  • deepseek-coder:33b

    • id: deepseek-coder:33b
    • maxLength: 16000 tokens
    • tokenLimit: 4096 tokens per request
    • requestLimit: 3000 requests per client
    • vendor: Ollama

These configurations have been validated and are ready for integration into the production environment

This commit introduces the following model configurations to the existing model registry:

- **yarn-mistral:7b-128k**
  - `id`: `yarn-mistral:7b-128k`
  - `maxLength`: 128000 tokens
  - `tokenLimit`: 4096 tokens per request
  - `requestLimit`: 3000 requests per client
  - `vendor`: `Ollama`

- **deepseek-coder:latest**
  - `id`: `deepseek-coder:latest`
  - `maxLength`: 16000 tokens
  - `tokenLimit`: 4096 tokens per request
  - `requestLimit`: 3000 requests per client
  - `vendor`: `Ollama`

- **deepseek-coder:6.7b**
  - `id`: `deepseek-coder:6.7b`
  - `maxLength`: 16000 tokens
  - `tokenLimit`: 4096 tokens per request
  - `requestLimit`: 3000 requests per client
  - `vendor`: `Ollama`

- **deepseek-coder:33b**
  - `id`: `deepseek-coder:33b`
  - `maxLength`: 16000 tokens
  - `tokenLimit`: 4096 tokens per request
  - `requestLimit`: 3000 requests per client
  - `vendor`: `Ollama`

These configurations have been validated and are ready for integration into the production environment
Copy link

vercel bot commented Nov 20, 2023

Someone is attempting to deploy a commit to a Personal Account owned by @jorge-menjivar on Vercel.

@jorge-menjivar first needs to authorize it.

Copy link

vercel bot commented Nov 20, 2023

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
unsaged ✅ Ready (Inspect) Visit Preview 💬 Add feedback Nov 20, 2023 7:35pm
unsaged-docs ✅ Ready (Inspect) Visit Preview 💬 Add feedback Nov 20, 2023 7:35pm

@vercel vercel bot temporarily deployed to Preview – unsaged November 20, 2023 19:34 Inactive
@vercel vercel bot temporarily deployed to Preview – unsaged-docs November 20, 2023 19:35 Inactive
@jorge-menjivar jorge-menjivar merged commit 2596be1 into jorge-menjivar:main Nov 20, 2023
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants