github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6392] Vision model prompt eval count in response is null or 1, what should be expected? #50527

New Issue
Open
opened 2026-04-28 16:10:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 16:10:42 -05:00
Owner
Copy Link

Originally created by @MarkWard0110 on GitHub (Aug 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6392

What is the issue?

When calling the chat completion for the following vision models, I get the following prompt eval count value.
llava:7b-v1.6-mistral-q4_0 -> prompt eval count 1
llava-llama3:8b-v1.1-q4_0 -> prompt eval count null
llava-phi3:3.8b-mini-fp16 -> prompt eval count 1

I don't know what I should expect for the prompt eval count when calling vision models. I'm not sure why llava-llama3 returned null when it generated a response.

What should be expected when calling vision models?

An example of the prompt is the following. The same image is used.

System
You are a helpful AI assistant

User
Describe what is in this image

Image

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.6

Originally created by @MarkWard0110 on GitHub (Aug 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6392 ### What is the issue? When calling the chat completion for the following vision models, I get the following prompt eval count value. llava:7b-v1.6-mistral-q4_0 -> prompt eval count `1` llava-llama3:8b-v1.1-q4_0 -> prompt eval count `null` llava-phi3:3.8b-mini-fp16 -> prompt eval count `1` I don't know what I should expect for the prompt eval count when calling vision models. I'm not sure why llava-llama3 returned null when it generated a response. What should be expected when calling vision models? An example of the prompt is the following. The same image is used. System You are a helpful AI assistant User Describe what is in this image Image <an image> ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.6
GiteaMirror added the bug label 2026-04-28 16:10:42 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#50527
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?