models(gallery): add lumimaid-v0.2-12b (#3020)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

gallery/index.yaml

@@ -488,6 +488,31 @@
     - filename: Mistral-Nemo-Instruct-2407-Q4_K_M.gguf
       sha256: 1a8b92fb546a80dce78151e4908f7bdb2c11fb3ef52af960e4bbe319a9cc5052
       uri: huggingface://bartowski/Mistral-Nemo-Instruct-2407-GGUF/Mistral-Nemo-Instruct-2407-Q4_K_M.gguf
+- !!merge <<: *mistral03
+  name: "lumimaid-v0.2-12b"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ep3ojmuMkFS-GmgRuI9iB.png
+  urls:
+    - https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B
+    - https://huggingface.co/mudler/Lumimaid-v0.2-12B-Q4_K_M-GGUF
+  description: |
+    This model is based on: Mistral-Nemo-Instruct-2407
+
+    Wandb: https://wandb.ai/undis95/Lumi-Mistral-Nemo?nw=nwuserundis95
+
+    NOTE: As explained on Mistral-Nemo-Instruct-2407 repo, it's recommended to use a low temperature, please experiment!
+
+    Lumimaid 0.1 -> 0.2 is a HUGE step up dataset wise.
+
+    As some people have told us our models are sloppy, Ikari decided to say fuck it and literally nuke all chats out with most slop.
+
+    Our dataset stayed the same since day one, we added data over time, cleaned them, and repeat. After not releasing model for a while because we were never satisfied, we think it's time to come back!
+  overrides:
+    parameters:
+      model: lumimaid-v0.2-12b-q4_k_m.gguf
+  files:
+    - filename: lumimaid-v0.2-12b-q4_k_m.gguf
+      sha256: f72299858a07e52be920b86d42ddcfcd5008b961d601ef6fd6a98a3377adccbf
+      uri: huggingface://mudler/Lumimaid-v0.2-12B-Q4_K_M-GGUF/lumimaid-v0.2-12b-q4_k_m.gguf
 - &mudler
   ### START mudler's LocalAI specific-models
   url: "github:mudler/LocalAI/gallery/mudler.yaml@master"