github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3128] nous-hermes2 stops generating output in the middle of a sentence #1925

New Issue
Closed
opened 2026-04-12 12:03:07 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 12:03:07 -05:00
Owner
Copy Link

Originally created by @aktersnurra on GitHub (Mar 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3128

Hello,

After a while of chatting with the nous-hermes2, around 4-10 questions, it stops generating output randomly mid-sentence. I have tried other models such as dolphin-mistral and openhermes, but I have not experienced similar behavior, however these are smaller models.

I cannot see any suspicious output from the logs.

Could this be an issue of VRAM on the GPU? (Only 8GB)

However, I see that there is never more than 6.8 GB allocated.

Anyone that might have a clue?

Originally created by @aktersnurra on GitHub (Mar 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3128 Hello, After a while of chatting with the nous-hermes2, around 4-10 questions, it stops generating output randomly mid-sentence. I have tried other models such as dolphin-mistral and openhermes, but I have not experienced similar behavior, however these are smaller models. I cannot see any suspicious output from the logs. Could this be an issue of VRAM on the GPU? (Only 8GB) However, I see that there is never more than 6.8 GB allocated. Anyone that might have a clue?
GiteaMirror added the bugneeds more info labels 2026-04-12 12:03:08 -05:00
GiteaMirror commented 2026-04-12 12:03:10 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Mar 13, 2024):

Hi @aktersnurra sorry about this. This is hard to troubleshoot.

Does the new recently released Nous Hermes 2 Pro 7B still have this problem? Someone has built a modelfile that you can use to import the model yourself or upload it to Ollama.com:

https://github.com/maxtheman/hermes-pro/blob/main/modelfile

Tagging @teknium1 for visibility and help.

<!-- gh-comment-id:1996140846 --> @mchiang0610 commented on GitHub (Mar 13, 2024): Hi @aktersnurra sorry about this. This is hard to troubleshoot. Does the new recently released Nous Hermes 2 Pro 7B still have this problem? Someone has built a modelfile that you can use to import the model yourself or upload it to Ollama.com: https://github.com/maxtheman/hermes-pro/blob/main/modelfile Tagging @teknium1 for visibility and help.
GiteaMirror commented 2026-04-12 12:03:10 -05:00
Author
Owner
Copy Link

@teknium1 commented on GitHub (Mar 14, 2024):

Are you using mixtral 8x7b or mistral 7b?

Hello,

After a while of chatting with the nous-hermes2, around 4-10 questions, it stops generating output randomly mid-sentence. I have tried other models such as dolphin-mistral and openhermes, but I have not experienced similar behavior, however these are smaller models.

I cannot see any suspicious output from the logs.

Could this be an issue of VRAM on the GPU? (Only 8GB)

However, I see that there is never more than 6.8 GB allocated.

Anyone that might have a clue?

<!-- gh-comment-id:1996696826 --> @teknium1 commented on GitHub (Mar 14, 2024): Are you using mixtral 8x7b or mistral 7b? > Hello, > > After a while of chatting with the nous-hermes2, around 4-10 questions, it stops generating output randomly mid-sentence. I have tried other models such as dolphin-mistral and openhermes, but I have not experienced similar behavior, however these are smaller models. > > I cannot see any suspicious output from the logs. > > Could this be an issue of VRAM on the GPU? (Only 8GB) > > However, I see that there is never more than 6.8 GB allocated. > > Anyone that might have a clue?
GiteaMirror commented 2026-04-12 12:03:11 -05:00
Author
Owner
Copy Link

@aktersnurra commented on GitHub (Mar 14, 2024):

Are you using mixtral 8x7b or mistral 7b?

Hello,
After a while of chatting with the nous-hermes2, around 4-10 questions, it stops generating output randomly mid-sentence. I have tried other models such as dolphin-mistral and openhermes, but I have not experienced similar behavior, however these are smaller models.
I cannot see any suspicious output from the logs.
Could this be an issue of VRAM on the GPU? (Only 8GB)
However, I see that there is never more than 6.8 GB allocated.
Anyone that might have a clue?

I am using the 11b:latest version.

Hi @aktersnurra sorry about this. This is hard to troubleshoot.

Does the new recently released Nous Hermes 2 Pro 7B still have this problem? Someone has built a modelfile that you can use to import the model yourself or upload it to Ollama.com:

https://github.com/maxtheman/hermes-pro/blob/main/modelfile

Tagging @teknium1 for visibility and help.

Thanks, I'll test this out and see if this model displays similar behavior or not.

<!-- gh-comment-id:1996817511 --> @aktersnurra commented on GitHub (Mar 14, 2024): > Are you using mixtral 8x7b or mistral 7b? > > > Hello, > > After a while of chatting with the nous-hermes2, around 4-10 questions, it stops generating output randomly mid-sentence. I have tried other models such as dolphin-mistral and openhermes, but I have not experienced similar behavior, however these are smaller models. > > I cannot see any suspicious output from the logs. > > Could this be an issue of VRAM on the GPU? (Only 8GB) > > However, I see that there is never more than 6.8 GB allocated. > > Anyone that might have a clue? I am using the [11b:latest](https://ollama.com/library/nous-hermes2) version. > Hi @aktersnurra sorry about this. This is hard to troubleshoot. > > Does the new recently released Nous Hermes 2 Pro 7B still have this problem? Someone has built a modelfile that you can use to import the model yourself or upload it to Ollama.com: > > https://github.com/maxtheman/hermes-pro/blob/main/modelfile > > Tagging @teknium1 for visibility and help. Thanks, I'll test this out and see if this model displays similar behavior or not.
GiteaMirror commented 2026-04-12 12:03:11 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 30, 2024):

If you're still having trouble with the model, please upgrade to the latest ollama to see if that clears it up. If not, let us know and I'll reopen the issue.

<!-- gh-comment-id:2384305793 --> @dhiltgen commented on GitHub (Sep 30, 2024): If you're still having trouble with the model, please upgrade to the latest ollama to see if that clears it up. If not, let us know and I'll reopen the issue.
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 needs more info
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#1925
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?