chore(model gallery): add ibm-granite_granite-3.2-8b-instruct (#4927)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-03-02 10:19:27 +01:00 committed by GitHub
parent 0a8ec1eb22
commit 0404d98190
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 58 additions and 0 deletions

View file

@ -1079,6 +1079,21 @@
- filename: MoE-Girl-800MA-3BT.Q4_K_M.gguf
sha256: 4c3cb57c27aadabd05573a1a01d6c7aee0f21620db919c7704f758d172e0bfa3
uri: huggingface://mradermacher/MoE-Girl-800MA-3BT-GGUF/MoE-Girl-800MA-3BT.Q4_K_M.gguf
- !!merge <<: *granite3
url: "github:mudler/LocalAI/gallery/granite3-2.yaml@master"
name: "ibm-granite_granite-3.2-8b-instruct"
urls:
- https://huggingface.co/ibm-granite/granite-3.2-8b-instruct
- https://huggingface.co/bartowski/ibm-granite_granite-3.2-8b-instruct-GGUF
description: |
Granite-3.2-8B-Instruct is an 8-billion-parameter, long-context AI model fine-tuned for thinking capabilities. Built on top of Granite-3.1-8B-Instruct, it has been trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks. The model allows controllability of its thinking capability, ensuring it is applied only when required.
overrides:
parameters:
model: ibm-granite_granite-3.2-8b-instruct-Q4_K_M.gguf
files:
- filename: ibm-granite_granite-3.2-8b-instruct-Q4_K_M.gguf
sha256: bd041eb5bc5e75e4f9a863372000046fd6490374f4dec07f399ca152b1df09c2
uri: huggingface://bartowski/ibm-granite_granite-3.2-8b-instruct-GGUF/ibm-granite_granite-3.2-8b-instruct-Q4_K_M.gguf
- name: "moe-girl-1ba-7bt-i1"
icon: https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/kTXXSSSqpb21rfyOX7FUa.jpeg
# chatml