mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-10-28 09:08:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

chore(gallery): add Mira v1.23 RLVR variants

Browse Source 
Add Q4_K_M and Q8_0 GGUF builds with the matching vision projector.
Pin downloads and verify SHA256 against LFS metadata and HTTP headers.
Document installation and explicit variant selection.

Assisted-by: Codex:gpt-6

(cherry picked from commit 472cddcaea, mudler/LocalAI#12635)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
localai-org-maint-bot authored and Ettore Di Giacinto committed 2026-10-13 07:31:06 +00:00
1 parent 45c6718013
commit 104c2ade47
1 file changed
+74
Download Patch File Download Diff File Expand all files Collapse all files
gallery/index.yaml
+74
View File
@@ -34062,6 +34062,80 @@
- filename: yanolja_YanoljaNEXT-Rosetta-12B-2510-Q4_K_M.gguf
sha256: 7531456d8886419d36ce103b1205cdc820865016bddc0b4671ec9910ba87071f
uri: huggingface://bartowski/yanolja_YanoljaNEXT-Rosetta-12B-2510-GGUF/yanolja_YanoljaNEXT-Rosetta-12B-2510-Q4_K_M.gguf
- name: mira-v1.23-27b-rlvr
variants:
- model: mira-v1.23-27b-rlvr-q8
url: github:mudler/LocalAI/gallery/gemma.yaml@master
urls:
- https://huggingface.co/Lambent/Mira-v1.23-27B-rlvr
- https://huggingface.co/mradermacher/Mira-v1.23-27B-rlvr-GGUF
description: |
Mira v1.23 RLVR is a 27B Gemma 3 fine-tune trained on creative writing,
roleplay, and problem-solving scenarios. This Q4_K_M GGUF build includes
the F16 vision projector for image input and uses the embedded chat template.
license: gemma
tags:
- llm
- chat
- vision
- gemma
- gguf
- cpu
- gpu
overrides:
backend: llama-cpp
context_size: 32768
mmproj: Mira-v1.23-27B-rlvr.mmproj-f16.gguf
options:
- use_jinja:true
template:
use_tokenizer_template: true
parameters:
model: Mira-v1.23-27B-rlvr.Q4_K_M.gguf
files:
- filename: Mira-v1.23-27B-rlvr.Q4_K_M.gguf
uri: https://huggingface.co/mradermacher/Mira-v1.23-27B-rlvr-GGUF/resolve/2aa3732dd7eee3c37f25d32cbc4b4341fa6fdf60/Mira-v1.23-27B-rlvr.Q4_K_M.gguf
sha256: 4de9289481a98bcf0f09a6967f06b758166bb31aca5f185cc6f54fb7a8954705
- filename: Mira-v1.23-27B-rlvr.mmproj-f16.gguf
uri: https://huggingface.co/mradermacher/Mira-v1.23-27B-rlvr-GGUF/resolve/2aa3732dd7eee3c37f25d32cbc4b4341fa6fdf60/Mira-v1.23-27B-rlvr.mmproj-f16.gguf
sha256: f71c9725dfe77b30e578c153f4ae207c51a98dbf93990cc4b22c4c693cc5fe71
- name: mira-v1.23-27b-rlvr-q8
url: github:mudler/LocalAI/gallery/gemma.yaml@master
urls:
- https://huggingface.co/Lambent/Mira-v1.23-27B-rlvr
- https://huggingface.co/mradermacher/Mira-v1.23-27B-rlvr-GGUF
description: |
Mira v1.23 RLVR is a 27B Gemma 3 fine-tune trained on creative writing,
roleplay, and problem-solving scenarios. This Q8_0 GGUF build includes
the F16 vision projector for image input and uses the embedded chat template.
license: gemma
tags:
- llm
- chat
- vision
- gemma
- gguf
- cpu
- gpu
overrides:
backend: llama-cpp
context_size: 32768
mmproj: Mira-v1.23-27B-rlvr.mmproj-f16.gguf
options:
- use_jinja:true
template:
use_tokenizer_template: true
parameters:
model: Mira-v1.23-27B-rlvr.Q8_0.gguf
files:
- filename: Mira-v1.23-27B-rlvr.Q8_0.gguf
uri: https://huggingface.co/mradermacher/Mira-v1.23-27B-rlvr-GGUF/resolve/2aa3732dd7eee3c37f25d32cbc4b4341fa6fdf60/Mira-v1.23-27B-rlvr.Q8_0.gguf
sha256: 59d284c9b3e5b68adbdbd8c11d205ef9fdc6cda195edf569296e011dd5f9e432
- filename: Mira-v1.23-27B-rlvr.mmproj-f16.gguf
uri: https://huggingface.co/mradermacher/Mira-v1.23-27B-rlvr-GGUF/resolve/2aa3732dd7eee3c37f25d32cbc4b4341fa6fdf60/Mira-v1.23-27B-rlvr.mmproj-f16.gguf
sha256: f71c9725dfe77b30e578c153f4ae207c51a98dbf93990cc4b22c4c693cc5fe71
- name: mira-v1.7-27b-i1
url: github:mudler/LocalAI/gallery/gemma.yaml@master
urls: