Add 4-bit quantization for Qwen3-1.7B

Qwen3-1.7B-GGUF/Q4_0.json

@@ -0,0 +1,14 @@
+{
+  "inference_type": "llama.cpp/text-to-text",
+  "schema_version": "1.0.0",
+  "load_time_parameters": {
+    "model": "https://huggingface.co/unsloth/Qwen3-1.7B-GGUF/resolve/main/Qwen3-1.7B-Q4_0.gguf"
+  },
+  "generation_time_parameters": {
+    "sampling_parameters": {
+      "temperature": 0.7,
+      "top_p": 0.8,
+      "repetition_penalty": 1.5
+    }
+  }
+}