Skip to content

GitLab

Explore

Sign in

Primary navigation

Project

Llama Index
- Activity
- Members
- Labels
- Issues
- Issue boards
- Milestones
- Iterations
- Wiki
- Environments
- Terraform modules
- Incidents
- Service Desk

Snippets Groups Projects

7c656548

Unverified Commit 7c656548 authored 11 months ago by Matthew Farrellee Committed by GitHub 11 months ago

Downloads
- Patches
- Plain Diff

set default max_tokens to 1024 (#13371)

if unset the service decides and picks a value small enough that users report the model is broken or not accurate

parent a11a953e

No related branches found

No related tags found

Loading

Changes 2

Hide whitespace changes

Inline Side-by-side

Showing

llama-index-integrations/llms/llama-index-llms-nvidia/llama_index/llms/nvidia/base.py 2 additions, 0 deletions

...s/llama-index-llms-nvidia/llama_index/llms/nvidia/base.py
llama-index-integrations/llms/llama-index-llms-nvidia/pyproject.toml 1 addition, 1 deletion

...-integrations/llms/llama-index-llms-nvidia/pyproject.toml

with 3 additions and 1 deletion

Loading

0% Loading or .

You are about to add 0 people to the discussion. Proceed with caution.

Finish editing this message first!

Please register or sign in to comment

Strive to be the person your dogs believe you are