chore(model gallery): add open-thoughts_openthinker3-7b (#5595)

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

gallery/index.yaml

@@ -7775,6 +7775,25 @@
     - filename: mmproj-Qwen2.5-Omni-7B-Q8_0.gguf
       sha256: 4a7bc5478a2ec8c5d186d63532eb22e75b79ba75ec3c0ce821676157318ef4ad
       uri: https://huggingface.co/ggml-org/Qwen2.5-Omni-7B-GGUF/resolve/main/mmproj-Qwen2.5-Omni-7B-Q8_0.gguf
+- !!merge <<: *qwen25
+  name: "open-thoughts_openthinker3-7b"
+  icon: https://huggingface.co/datasets/open-thoughts/open-thoughts-114k/resolve/main/open_thoughts.png
+  urls:
+    - https://huggingface.co/open-thoughts/OpenThinker3-7B
+    - https://huggingface.co/bartowski/open-thoughts_OpenThinker3-7B-GGUF
+  description: |
+    State-of-the-art open-data 7B reasoning model. 🚀
+
+    This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the OpenThoughts3-1.2M dataset. It represents a notable improvement over our previous models, OpenThinker-7B and OpenThinker2-7B, and it outperforms several other strong reasoning 7B models such as DeepSeek-R1-Distill-Qwen-7B and Llama-3.1-Nemotron-Nano-8B-v1, despite being trained only with SFT, without any RL.
+
+    This time, we also released a paper! See our paper and blog post for more details. OpenThinker3-32B to follow! 👀
+  overrides:
+    parameters:
+      model: open-thoughts_OpenThinker3-7B-Q4_K_M.gguf
+  files:
+    - filename: open-thoughts_OpenThinker3-7B-Q4_K_M.gguf
+      sha256: 73b8f44c3b11c3ec63e4c4ddbb262679c8f681511d84940c4c990814aa0bafc0
+      uri: huggingface://bartowski/open-thoughts_OpenThinker3-7B-GGUF/open-thoughts_OpenThinker3-7B-Q4_K_M.gguf
 - &llama31
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
   icon: https://avatars.githubusercontent.com/u/153379578