models(gallery): add lumimaid-8b (#3026)

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

gallery/index.yaml

@@ -196,6 +196,29 @@
     - filename: Llama-3.1-8B-Instruct-Fei-v1-Uncensored.Q4_K_M.gguf
       sha256: 12fef8ff0a5c4cf6988523d33d89287edb7531f0d1644707548f45f1387e398a
       uri: huggingface://mradermacher/Llama-3.1-8B-Instruct-Fei-v1-Uncensored-GGUF/Llama-3.1-8B-Instruct-Fei-v1-Uncensored.Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "lumimaid-v0.2-8b"
+  urls:
+    - https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B
+    - https://huggingface.co/mradermacher/Lumimaid-v0.2-8B-GGUF
+  icon: https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/TUcHg7LKNjfo0sni88Ps7.png
+  description: |
+      This model is based on: Meta-Llama-3.1-8B-Instruct
+
+      Wandb: https://wandb.ai/undis95/Lumi-Llama-3-1-8B?nw=nwuserundis95
+
+      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-v0.2-8B.Q4_K_M.gguf
+  files:
+    - filename: Lumimaid-v0.2-8B.Q4_K_M.gguf
+      sha256: c8024fcb49c71410903d0d076a1048249fa48b31637bac5177bf5c3f3d603d85
+      uri: huggingface://mradermacher/Lumimaid-v0.2-8B-GGUF/Lumimaid-v0.2-8B.Q4_K_M.gguf
 - &deepseek
   ## Deepseek
   url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"