mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 09:08:54 -04:00
feat(gallery): add Sage-A1.5 GGUF variants
Offer the official Q4_K_M and Q8_0 builds with their vision projector.
Pin artifact revisions and document installation and variant selection.
Assisted-by: Codex:gpt-6
(cherry picked from commit 9f98baa8e5, mudler/LocalAI#12833)
Assisted-by: Claude:claude-sonnet-5-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
localai-org-maint-bot authored and Ettore Di Giacinto committed
1 parent
d06c255797
commit
c08e37f55d
2 files changed
+180
No files matched your search
@@ -3,6 +3,88 @@
|
||||
# written by scripts/models/cmd/modelcatalog and stays only so releases before
|
||||
# the cutover keep working. CI fails when it differs from the generated copy:
|
||||
# go run ./scripts/models/cmd/modelcatalog --library gallery/models/index.yaml --out gallery/index.yaml
|
||||
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
name: sage-a1.5-q4
|
||||
description: |
|
||||
Sage-A1.5 is a 35B mixture-of-experts model based on Qwen3.6 for
|
||||
scientific reasoning, coding, and tool use. This official Q4_K_M GGUF
|
||||
build uses llama.cpp and includes the vision projector.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/InternScience/Sage-A1.5
|
||||
- https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- vision
|
||||
- reasoning
|
||||
- cpu
|
||||
- gpu
|
||||
files:
|
||||
- filename: Sage-A1.5-Q4_K_M.gguf
|
||||
sha256: a64fe0bbf936db3eb54f66f142c2b2eee569ade83673649f549a21daef8ca395
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF/resolve/10b179b52f2c841030db327627e707d076b4c8cf/Sage-A1.5-Q4_K_M.gguf
|
||||
- filename: Sage-A1.5-mmproj.gguf
|
||||
sha256: 51cd4410057e8dc4152ca771a726fbfb34856f047e7049018c757d42ddd481f2
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF/resolve/10b179b52f2c841030db327627e707d076b4c8cf/Sage-A1.5-mmproj.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
- vision
|
||||
mmproj: Sage-A1.5-mmproj.gguf
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Sage-A1.5-Q4_K_M.gguf
|
||||
temperature: 1.0
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
variants:
|
||||
- model: sage-a1.5-q8
|
||||
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
name: sage-a1.5-q8
|
||||
description: |
|
||||
Sage-A1.5 is a 35B mixture-of-experts model based on Qwen3.6 for
|
||||
scientific reasoning, coding, and tool use. This official Q8_0 GGUF
|
||||
build uses llama.cpp and includes the vision projector.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/InternScience/Sage-A1.5
|
||||
- https://huggingface.co/InternScience/Sage-A1.5-Q8_0-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- vision
|
||||
- reasoning
|
||||
- cpu
|
||||
- gpu
|
||||
files:
|
||||
- filename: Sage-A1.5-Q8_0.gguf
|
||||
sha256: f7247f6faef3f6c616b953595e1fc7c3fbf257d02d9915af5fdf15e808ea8ee4
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q8_0-GGUF/resolve/1cbe2925983a13a6c09881b9bc088884dbfbc146/Sage-A1.5-Q8_0.gguf
|
||||
- filename: Sage-A1.5-mmproj.gguf
|
||||
sha256: 51cd4410057e8dc4152ca771a726fbfb34856f047e7049018c757d42ddd481f2
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF/resolve/10b179b52f2c841030db327627e707d076b4c8cf/Sage-A1.5-mmproj.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
- vision
|
||||
mmproj: Sage-A1.5-mmproj.gguf
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Sage-A1.5-Q8_0.gguf
|
||||
temperature: 1.0
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
name: lfm2.5-24b-a2b-turbo-brilliance-iq4-xs
|
||||
description: |
|
||||
|
||||
@@ -4,6 +4,104 @@
|
||||
# changes and never edit it by hand. CI fails when it is stale. A build from
|
||||
# master reads it as the default model source; a tagged build reads the gallery
|
||||
# until the release cutover.
|
||||
- kind: model
|
||||
id: sage-a1.5-q4
|
||||
name: sage-a1.5-q4
|
||||
version: 0.0.0-gallery.88087a1aab17
|
||||
description: |
|
||||
Sage-A1.5 is a 35B mixture-of-experts model based on Qwen3.6 for
|
||||
scientific reasoning, coding, and tool use. This official Q4_K_M GGUF
|
||||
build uses llama.cpp and includes the vision projector.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/InternScience/Sage-A1.5
|
||||
- https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- vision
|
||||
- reasoning
|
||||
- cpu
|
||||
- gpu
|
||||
channel: gallery
|
||||
policy:
|
||||
requireSignature: false
|
||||
schemaVersion: 1
|
||||
model:
|
||||
url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
files:
|
||||
- filename: Sage-A1.5-Q4_K_M.gguf
|
||||
sha256: a64fe0bbf936db3eb54f66f142c2b2eee569ade83673649f549a21daef8ca395
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF/resolve/10b179b52f2c841030db327627e707d076b4c8cf/Sage-A1.5-Q4_K_M.gguf
|
||||
- filename: Sage-A1.5-mmproj.gguf
|
||||
sha256: 51cd4410057e8dc4152ca771a726fbfb34856f047e7049018c757d42ddd481f2
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF/resolve/10b179b52f2c841030db327627e707d076b4c8cf/Sage-A1.5-mmproj.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
- vision
|
||||
mmproj: Sage-A1.5-mmproj.gguf
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Sage-A1.5-Q4_K_M.gguf
|
||||
temperature: 1.0
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
variants:
|
||||
- model: sage-a1.5-q8
|
||||
- kind: model
|
||||
id: sage-a1.5-q8
|
||||
name: sage-a1.5-q8
|
||||
version: 0.0.0-gallery.d2ee65a3043e
|
||||
description: |
|
||||
Sage-A1.5 is a 35B mixture-of-experts model based on Qwen3.6 for
|
||||
scientific reasoning, coding, and tool use. This official Q8_0 GGUF
|
||||
build uses llama.cpp and includes the vision projector.
|
||||
license: apache-2.0
|
||||
urls:
|
||||
- https://huggingface.co/InternScience/Sage-A1.5
|
||||
- https://huggingface.co/InternScience/Sage-A1.5-Q8_0-GGUF
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- vision
|
||||
- reasoning
|
||||
- cpu
|
||||
- gpu
|
||||
channel: gallery
|
||||
policy:
|
||||
requireSignature: false
|
||||
schemaVersion: 1
|
||||
model:
|
||||
url: github:mudler/LocalAI/gallery/virtual.yaml@master
|
||||
files:
|
||||
- filename: Sage-A1.5-Q8_0.gguf
|
||||
sha256: f7247f6faef3f6c616b953595e1fc7c3fbf257d02d9915af5fdf15e808ea8ee4
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q8_0-GGUF/resolve/1cbe2925983a13a6c09881b9bc088884dbfbc146/Sage-A1.5-Q8_0.gguf
|
||||
- filename: Sage-A1.5-mmproj.gguf
|
||||
sha256: 51cd4410057e8dc4152ca771a726fbfb34856f047e7049018c757d42ddd481f2
|
||||
uri: https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF/resolve/10b179b52f2c841030db327627e707d076b4c8cf/Sage-A1.5-mmproj.gguf
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 32768
|
||||
known_usecases:
|
||||
- chat
|
||||
- vision
|
||||
mmproj: Sage-A1.5-mmproj.gguf
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
model: Sage-A1.5-Q8_0.gguf
|
||||
temperature: 1.0
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
- kind: model
|
||||
id: lfm2.5-24b-a2b-turbo-brilliance-iq4-xs
|
||||
name: lfm2.5-24b-a2b-turbo-brilliance-iq4-xs
|
||||
|
||||
Reference in new issue
Block a user