models(gallery): add smollm2-1.7b-instruct (#4033)

Signed-off-by: Ettore Di Giacinto <[email protected]>

gallery/index.yaml

@@ -861,6 +861,23 @@
     - filename: SmolLM-1.7B-Instruct.Q4_K_M.gguf
       sha256: 2b07eb2293ed3fc544a9858beda5bfb03dcabda6aa6582d3c85768c95f498d28
       uri: huggingface://MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF/SmolLM-1.7B-Instruct.Q4_K_M.gguf
+- !!merge <<: *smollm
+  name: "smollm2-1.7b-instruct"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/y45hIMNREW7w_XpHYB_0q.png
+  urls:
+    - https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct
+    - https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF
+  description: |
+    SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device.
+
+    The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics. It was trained on 11 trillion tokens using a diverse dataset combination: FineWeb-Edu, DCLM, The Stack, along with new mathematics and coding datasets that we curated and will release soon. We developed the instruct version through supervised fine-tuning (SFT) using a combination of public datasets and our own curated datasets. We then applied Direct Preference Optimization (DPO) using UltraFeedback.
+  overrides:
+    parameters:
+      model: smollm2-1.7b-instruct-q4_k_m.gguf
+  files:
+    - filename: smollm2-1.7b-instruct-q4_k_m.gguf
+      sha256: decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33
+      uri: huggingface://HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF/smollm2-1.7b-instruct-q4_k_m.gguf
 - &llama31
   ## LLama3.1
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master"