ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-04-26 05:50:01 +00:00
Code Issues Actions 15 Packages Projects Releases Wiki Activity

chore(model gallery) update gemma3 qat models

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-20 10:11:12 +02:00
parent e495b89f18
commit 4bc4b1e8bc
1 changed files with 14 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
gallery/index.yaml
View File

@ -82,7 +82,7 @@
name: "gemma-3-12b-it-qat" name: "gemma-3-12b-it-qat"
urls: urls:
- https://huggingface.co/google/gemma-3-12b-it - https://huggingface.co/google/gemma-3-12b-it
- https://huggingface.co/vinimuchulski/gemma-3-12b-it-qat-q4_0-gguf - https://huggingface.co/bartowski/google_gemma-3-12b-it-qat-GGUF
description: | description: |
This model corresponds to the 12B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization. This model corresponds to the 12B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.
@ -91,16 +91,16 @@
You can find the half-precision version here. You can find the half-precision version here.
overrides: overrides:
parameters: parameters:
model: gemma-3-12b-it-q4_0.gguf model: google_gemma-3-12b-it-qat-Q4_0.gguf
files: files:
- filename: gemma-3-12b-it-q4_0.gguf - filename: google_gemma-3-12b-it-qat-Q4_0.gguf
sha256: 6f1bb5f455414f7b46482bda51cbfdbf19786e21a5498c4403fdfc03d09b045c sha256: 2ad4c9ce431a2d5b80af37983828c2cfb8f4909792ca5075e0370e3a71ca013d
uri: huggingface://vinimuchulski/gemma-3-12b-it-qat-q4_0-gguf/gemma-3-12b-it-q4_0.gguf uri: huggingface://bartowski/google_gemma-3-12b-it-qat-GGUF/google_gemma-3-12b-it-qat-Q4_0.gguf
- !!merge <<: *gemma3 - !!merge <<: *gemma3
name: "gemma-3-4b-it-qat" name: "gemma-3-4b-it-qat"
urls: urls:
- https://huggingface.co/google/gemma-3-4b-it - https://huggingface.co/google/gemma-3-4b-it
- https://huggingface.co/vinimuchulski/gemma-3-4b-it-qat-q4_0-gguf - https://huggingface.co/bartowski/google_gemma-3-4b-it-qat-GGUF
description: | description: |
This model corresponds to the 4B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization. This model corresponds to the 4B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.
@ -109,16 +109,16 @@
You can find the half-precision version here. You can find the half-precision version here.
overrides: overrides:
parameters: parameters:
model: gemma-3-4b-it-q4_0.gguf model: google_gemma-3-4b-it-qat-Q4_0.gguf
files: files:
- filename: gemma-3-4b-it-q4_0.gguf - filename: google_gemma-3-4b-it-qat-Q4_0.gguf
sha256: 2ca493d426ffcb43db27132f183a0230eda4a3621e58b328d55b665f1937a317 sha256: 0231e2cba887f4c7834c39b34251e26b2eebbb71dfac0f7e6e2b2c2531c1a583
uri: huggingface://vinimuchulski/gemma-3-4b-it-qat-q4_0-gguf/gemma-3-4b-it-q4_0.gguf uri: huggingface://bartowski/google_gemma-3-4b-it-qat-GGUF/google_gemma-3-4b-it-qat-Q4_0.gguf
- !!merge <<: *gemma3 - !!merge <<: *gemma3
name: "gemma-3-27b-it-qat" name: "gemma-3-27b-it-qat"
urls: urls:
- https://huggingface.co/google/gemma-3-27b-it - https://huggingface.co/google/gemma-3-27b-it
- https://huggingface.co/vinimuchulski/gemma-3-27b-it-qat-q4_0-gguf - https://huggingface.co/bartowski/google_gemma-3-27b-it-qat-GGUF
description: | description: |
This model corresponds to the 27B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization. This model corresponds to the 27B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization.
@ -127,11 +127,11 @@
You can find the half-precision version here. You can find the half-precision version here.
overrides: overrides:
parameters: parameters:
model: gemma-3-27b-it-q4_0.gguf model: google_gemma-3-27b-it-qat-Q4_0.gguf
files: files:
- filename: gemma-3-27b-it-q4_0.gguf - filename: gemma-3-27b-it-q4_0.gguf
sha256: 45e586879bc5f5d7a5b6527e812952057ce916d9fc7ba16f7262ec9972c9e2a2 sha256: 4f1e32db877a9339df2d6529c1635570425cbe81f0aa3f7dd5d1452f2e632b42
uri: huggingface://vinimuchulski/gemma-3-27b-it-qat-q4_0-gguf/gemma-3-27b-it-q4_0.gguf uri: huggingface://bartowski/google_gemma-3-27b-it-qat-GGUF/google_gemma-3-27b-it-qat-Q4_0.gguf
- !!merge <<: *gemma3 - !!merge <<: *gemma3
name: "qgallouedec_gemma-3-27b-it-codeforces-sft" name: "qgallouedec_gemma-3-27b-it-codeforces-sft"
urls: urls: