Ian Eaves
db8bb5d9df
adds support for hosted chat providers
...
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com >
2026-01-24 16:00:59 -06:00
Mike Bonnet
95b13e209e
s390x: switch to a smaller bigendian model for testing
...
Should improve performance of integration tests.
Signed-off-by: Mike Bonnet <mikeb@redhat.com >
2025-09-11 06:33:54 -07:00
Mike Bonnet
cb67ddc4dd
use bigendian models when testing bigendian arches
...
Signed-off-by: Mike Bonnet <mikeb@redhat.com >
2025-09-10 23:06:43 -07:00
Oliver Walsh
912bf92d6f
Use Hugging Face models for tinylama and smollm:135
...
The chat templates from the ollama models do not work with llama.cpp after
converting (successfully) to jinja2.
Workaround by creating shortname.conf aliases to equivalent models on
Hugging Face.
Signed-off-by: Oliver Walsh <owalsh@redhat.com >
2025-09-10 14:38:26 +01:00
Oliver Walsh
4e96af0fb0
Revert back to ollama granite-code models
...
The issue with the ollama granite-code models are now resolved with
https://github.com/containers/ramalama/pull/1856
https://github.com/containers/ramalama/pull/1858
Revert the changes from da7eb54046#1374
Signed-off-by: Oliver Walsh <owalsh@redhat.com >
2025-08-28 17:42:42 +01:00
Daniel J Walsh
de5ed5dd6a
Sort shortnames alphabetically
...
Signed-off-by: Daniel J Walsh <dwalsh@redhat.com >
2025-08-12 05:02:09 -04:00
Daniel J Walsh
e4a833feb0
Add gpt-oss models to shortnames.conf
...
Fixes: https://github.com/containers/ramalama/issues/1805
Signed-off-by: Daniel J Walsh <dwalsh@redhat.com >
2025-08-11 16:06:07 -04:00
Eric Curtin
fa2f485175
Mistral should point to lmstudio gguf
...
I don't know who MaziyarPanahi is, but I know who lmstudio are
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-07-15 15:04:54 +01:00
Eric Curtin
089589cdfe
Add gemma aliases
...
The ollama variants are incompatible
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-06-27 15:28:00 +01:00
Eric Curtin
9bc76c2757
This is not a multi-model model
...
Although the other gemma once are. Point the user towards a single
gguf.
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-06-10 18:43:06 +01:00
Eric Curtin
e494a6d924
Add smolvlm vision models
...
For multimodal usage
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-05-18 12:02:01 +01:00
Eric Curtin
2c48af0175
Add shortnames for mistral-small3.1 model
...
Another Ollama model that's only compatible with Ollama's forking
of llama.cpp
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-05-01 17:48:46 +01:00
Eric Curtin
35cbabdb74
Add gemma3 shortnames
...
Otherwise we will pull the incompatible gguf's from Ollama
registry.
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-04-25 18:06:06 +01:00
Daniel J Walsh
974a37fe00
Add shortname for deepseek
...
Signed-off-by: Daniel J Walsh <dwalsh@redhat.com >
2025-01-27 10:02:26 -05:00
Eric Curtin
da7eb54046
granite-code models in Ollama are malformed
...
To the extent where they work in Ollama but not vanilla llama.cpp
This is sortof a workaround, pulling the hf versions.
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-01-13 17:27:50 +00:00
Eric Curtin
a9ecebc190
smollm:135m for testing purposes
...
smollm is a model by Hugging Face, it's good for testing and CPU
inferencing.
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-01-09 16:04:15 +00:00
Eric Curtin
65f02b8051
Update shortnames.conf to alias new granite models
...
This updates the shortnames for the "granite" models to point to newer
versions.
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2024-12-18 17:42:01 +00:00
Daniel J Walsh
e4112a60e8
Add granite-8b to shortnames.conf
...
Signed-off-by: Daniel J Walsh <dwalsh@redhat.com >
2024-11-12 10:08:31 -07:00
swarajpande5
8cef39b8b4
Fix shortname paths
...
Signed-off-by: swarajpande5 <swarajpande5@gmail.com >
2024-10-25 20:17:44 +05:30
Michael Clifford
2f01df54ce
add AI Lab models to shortnames
...
Signed-off-by: Michael Clifford <mcliffor@redhat.com >
2024-10-21 12:02:14 -04:00
Daniel J Walsh
71eeacdd93
Cleanup and install shortnames files
...
Signed-off-by: Daniel J Walsh <dwalsh@redhat.com >
2024-09-19 13:44:50 -04:00
