github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6388] The Hermes 3 Series of Models #4013

New Issue
Closed
opened 2026-04-12 14:53:01 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-04-12 14:53:01 -05:00
Owner
Copy Link

Originally created by @tomasmcm on GitHub (Aug 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6388

https://huggingface.co/collections/NousResearch/hermes-3-66bd6c01399b14b08fe335ea

https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B
https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B
https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B

https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF
https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B-GGUF

Originally created by @tomasmcm on GitHub (Aug 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6388 https://huggingface.co/collections/NousResearch/hermes-3-66bd6c01399b14b08fe335ea https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B-GGUF
GiteaMirror added the model label 2026-04-12 14:53:01 -05:00
GiteaMirror commented 2026-04-12 14:53:03 -05:00
Author
Owner
Copy Link

@MaxJa4 commented on GitHub (Aug 16, 2024):

Got some 8B and 70B quants up: https://ollama.com/finalend/hermes-3-llama-3.1

<!-- gh-comment-id:2293361753 --> @MaxJa4 commented on GitHub (Aug 16, 2024): Got some 8B and 70B quants up: https://ollama.com/finalend/hermes-3-llama-3.1
GiteaMirror commented 2026-04-12 14:53:03 -05:00
Author
Owner
Copy Link

@vikanezrimaya commented on GitHub (Aug 16, 2024):

Related: #6390 (tool calling format seems different from Llama 3.1 — code changes may be required to support hermes tool calling format?)

<!-- gh-comment-id:2293566429 --> @vikanezrimaya commented on GitHub (Aug 16, 2024): Related: #6390 (tool calling format seems different from Llama 3.1 — code changes may be required to support hermes tool calling format?)
GiteaMirror commented 2026-04-12 14:53:03 -05:00
Author
Owner
Copy Link

@MaxJa4 commented on GitHub (Aug 16, 2024):

Updated model tags with the changes of #6390

<!-- gh-comment-id:2294227022 --> @MaxJa4 commented on GitHub (Aug 16, 2024): Updated model tags with the changes of #6390
GiteaMirror commented 2026-04-12 14:53:04 -05:00
Author
Owner
Copy Link

@wwjCMP commented on GitHub (Aug 18, 2024):

Updated model tags with the changes of #6390

hermes-3-llama-3.1:8b-q8_0 has an infinite output issue .

<!-- gh-comment-id:2295219938 --> @wwjCMP commented on GitHub (Aug 18, 2024): > Updated model tags with the changes of #6390 hermes-3-llama-3.1:8b-q8_0 has an infinite output issue .
GiteaMirror commented 2026-04-12 14:53:04 -05:00
Author
Owner
Copy Link

@MaxJa4 commented on GitHub (Aug 18, 2024):

hermes-3-llama-3.1:8b-q8_0 has an infinite output issue .

Works fine on my end, what prompt did you use?
Did you set any parameters or changed anything or is everything default (e.g. by just using ollama run in the console)?
Is it only for the Q8 quant?

<!-- gh-comment-id:2295227104 --> @MaxJa4 commented on GitHub (Aug 18, 2024): > hermes-3-llama-3.1:8b-q8_0 has an infinite output issue . Works fine on my end, what prompt did you use? Did you set any parameters or changed anything or is everything default (e.g. by just using `ollama run` in the console)? Is it only for the Q8 quant?
GiteaMirror commented 2026-04-12 14:53:05 -05:00
Author
Owner
Copy Link

@wwjCMP commented on GitHub (Aug 18, 2024):

hermes-3-llama-3.1:8b-q8_0 has an infinite output issue .

Works fine on my end, what prompt did you use? Did you set any parameters or changed anything or is everything default (e.g. by just using ollama run in the console)? Is it only for the Q8 quant?

I use it in a RAG flow.
This issue just happens sometimes.
It may be a problem with the model itself. 

<!-- gh-comment-id:2295236485 --> @wwjCMP commented on GitHub (Aug 18, 2024): > > hermes-3-llama-3.1:8b-q8_0 has an infinite output issue . > > Works fine on my end, what prompt did you use? Did you set any parameters or changed anything or is everything default (e.g. by just using `ollama run` in the console)? Is it only for the Q8 quant? I use it in a RAG flow. This issue just happens sometimes. It may be a problem with the model itself. 
GiteaMirror commented 2026-04-12 14:53:05 -05:00
Author
Owner
Copy Link

@wwjCMP commented on GitHub (Aug 18, 2024):

hermes-3-llama-3.1:8b-q8_0 has an infinite output issue .

Works fine on my end, what prompt did you use? Did you set any parameters or changed anything or is everything default (e.g. by just using ollama run in the console)? Is it only for the Q8 quant?

After testing, it sometimes keeps repeating previous answers in simple Q&A.

<!-- gh-comment-id:2295243527 --> @wwjCMP commented on GitHub (Aug 18, 2024): > > hermes-3-llama-3.1:8b-q8_0 has an infinite output issue . > > Works fine on my end, what prompt did you use? Did you set any parameters or changed anything or is everything default (e.g. by just using `ollama run` in the console)? Is it only for the Q8 quant? After testing, it sometimes keeps repeating previous answers in simple Q&A.
GiteaMirror commented 2026-04-12 14:53:06 -05:00
Author
Owner
Copy Link

@MaxJa4 commented on GitHub (Aug 18, 2024):

Tried it with Q&A both within the context window and outside it. Both worked flawlessly. Do you change/supply any parameters? Is context not cleared between sessions?

<!-- gh-comment-id:2295269329 --> @MaxJa4 commented on GitHub (Aug 18, 2024): Tried it with Q&A both within the context window and outside it. Both worked flawlessly. Do you change/supply any parameters? Is context not cleared between sessions?
GiteaMirror commented 2026-04-12 14:53:06 -05:00
Author
Owner
Copy Link

@ross-rosario commented on GitHub (Aug 24, 2024):

Any impediments to adding that set of models?

<!-- gh-comment-id:2308367007 --> @ross-rosario commented on GitHub (Aug 24, 2024): Any impediments to adding that set of models?
GiteaMirror commented 2026-04-12 14:53:06 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Sep 4, 2024):

Hi all, these should be uploaded now: https://ollama.com/library/hermes3

<!-- gh-comment-id:2329058224 --> @jmorganca commented on GitHub (Sep 4, 2024): Hi all, these should be uploaded now: https://ollama.com/library/hermes3
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 model
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#4013
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?