[GH-ISSUE #2919] Loading model into memory instead of generating chat completion. #27550

Closed
opened 2026-04-22 04:57:33 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @RapierXbox on GitHub (Mar 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2919

Hi, i am trying to do a chat completion with llama2 and it seems like its loading up a model instead of generating a chat completion. { "model": "llama2, "message": [ { "role": "user", "content": "hello" } ], "stream": "false" } and its returning nothing.

Originally created by @RapierXbox on GitHub (Mar 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2919 Hi, i am trying to do a chat completion with llama2 and it seems like its loading up a model instead of generating a chat completion. `{ "model": "llama2, "message": [ { "role": "user", "content": "hello" } ], "stream": "false" }` and its returning nothing.
Author
Owner

@RapierXbox commented on GitHub (Mar 4, 2024):

ok i fixed it... i used the wrong api endpoint

<!-- gh-comment-id:1977246128 --> @RapierXbox commented on GitHub (Mar 4, 2024): ok i fixed it... i used the wrong api endpoint
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#27550