github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6956] Why doesn't the model know which model it is? #66450

New Issue
Closed
opened 2026-05-04 05:28:09 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-04 05:28:09 -05:00
Owner
Copy Link

Originally created by @robotom on GitHub (Sep 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6956

What is the issue?

If I load llama 3.1 8B and ask it which model it is, it does not know what LLaMa 3.1 is at all. Sometimes it thinks it's LLama 3 or a 7B param model. Is there any reason for this? How can I be sure what I am running except for whatever ollama ps reports?

(running on 4070 8GB VRAM and i7-13700HX)

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

ollama 3.1:8B

Originally created by @robotom on GitHub (Sep 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6956 ### What is the issue? If I load llama 3.1 8B and ask it which model it is, it does not know what LLaMa 3.1 is at all. Sometimes it thinks it's LLama 3 or a 7B param model. Is there any reason for this? How can I be sure what I am running except for whatever `ollama ps` reports? (running on 4070 8GB VRAM and i7-13700HX) ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version ollama 3.1:8B
GiteaMirror added the question label 2026-05-04 05:28:09 -05:00
GiteaMirror commented 2026-05-04 05:28:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2024):

Models don't "know" anything, they're fancy autocomplete based on a large corpus of random information. You can provide a model with guidance with context or system prompts and it will generate seemingly authoritative statements, but if you want actual facts, you can't rely on a model.

<!-- gh-comment-id:2374476425 --> @rick-github commented on GitHub (Sep 25, 2024): Models don't "know" anything, they're fancy autocomplete based on a large corpus of random information. You can provide a model with guidance with context or system prompts and it will generate seemingly authoritative statements, but if you want actual facts, you can't rely on a model.
GiteaMirror commented 2026-05-04 05:28:37 -05:00
Author
Owner
Copy Link

@robotom commented on GitHub (Sep 25, 2024):

Models don't "know" anything, they're fancy autocomplete based on a large corpus of random information. You can provide a model with guidance with context or system prompts and it will generate seemingly authoritative statements, but if you want actual facts, you can't rely on a model.

Valid, though it is overtly unaware of the existence of LLaMa 3.1 at all. It knows about couscous recipes and recent news up until the cutoff. Shouldn't it at least have that training data? Seems odd.

<!-- gh-comment-id:2374500704 --> @robotom commented on GitHub (Sep 25, 2024): > Models don't "know" anything, they're fancy autocomplete based on a large corpus of random information. You can provide a model with guidance with context or system prompts and it will generate seemingly authoritative statements, but if you want actual facts, you can't rely on a model. Valid, though it is overtly unaware of the existence of LLaMa 3.1 at all. It knows about couscous recipes and recent news up until the cutoff. Shouldn't it at least have that training data? Seems odd.
GiteaMirror commented 2026-05-04 05:28:41 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 26, 2024):

How the models respond to these sorts of questions is based on how they're trained (or fine tuned) and you'll see varying results from different models. Try different models out to find the one that best suits your needs.

<!-- gh-comment-id:2377378573 --> @dhiltgen commented on GitHub (Sep 26, 2024): How the models respond to these sorts of questions is based on how they're trained (or fine tuned) and you'll see varying results from different models. Try different models out to find the one that best suits your needs.
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 question
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#66450
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?