[Model] Add Qwen2.5-1.5B Math (#567)

Add the following model to prebuilt list: - `Qwen2.5-Math-1.5B-Instruct-q4f16_1-MLC` - `Qwen2.5-Math-1.5B-Instruct-q4f32_1-MLC`
mlc-ai · Sep 19, 2024 · 8094abf · 8094abf
1 parent bdfb62f
commit 8094abf
Showing 1 changed file with 60 additions and 31 deletions.
diff --git a/src/config.ts b/src/config.ts
@@ -1041,11 +1041,11 @@ export const prebuiltAppConfig: AppConfig = {
         context_window_size: 4096,
       },
     },
-    // Qwen2-Math
+    // Qwen2.5-Math
     {
       model:
-        "https://huggingface.co/mlc-ai/Qwen2-Math-1.5B-Instruct-q4f16_1-MLC",
-      model_id: "Qwen2-Math-1.5B-Instruct-q4f16_1-MLC",
+        "https://huggingface.co/mlc-ai/Qwen2.5-Math-1.5B-Instruct-q4f16_1-MLC",
+      model_id: "Qwen2.5-Math-1.5B-Instruct-q4f16_1-MLC",
       model_lib:
         modelLibURLPrefix +
         modelVersion +
@@ -1058,8 +1058,8 @@ export const prebuiltAppConfig: AppConfig = {
     },
     {
       model:
-        "https://huggingface.co/mlc-ai/Qwen2-Math-1.5B-Instruct-q4f32_1-MLC",
-      model_id: "Qwen2-Math-1.5B-Instruct-q4f32_1-MLC",
+        "https://huggingface.co/mlc-ai/Qwen2.5-Math-1.5B-Instruct-q4f32_1-MLC",
+      model_id: "Qwen2.5-Math-1.5B-Instruct-q4f32_1-MLC",
       model_lib:
         modelLibURLPrefix +
         modelVersion +
@@ -1070,32 +1070,6 @@ export const prebuiltAppConfig: AppConfig = {
         context_window_size: 4096,
       },
     },
-    {
-      model: "https://huggingface.co/mlc-ai/Qwen2-Math-7B-Instruct-q4f16_1-MLC",
-      model_id: "Qwen2-Math-7B-Instruct-q4f16_1-MLC",
-      model_lib:
-        modelLibURLPrefix +
-        modelVersion +
-        "/Qwen2-7B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasm",
-      low_resource_required: false,
-      vram_required_MB: 5106.67,
-      overrides: {
-        context_window_size: 4096,
-      },
-    },
-    {
-      model: "https://huggingface.co/mlc-ai/Qwen2-Math-7B-Instruct-q4f32_1-MLC",
-      model_id: "Qwen2-Math-7B-Instruct-q4f32_1-MLC",
-      model_lib:
-        modelLibURLPrefix +
-        modelVersion +
-        "/Qwen2-7B-Instruct-q4f32_1-ctx4k_cs1k-webgpu.wasm",
-      low_resource_required: false,
-      vram_required_MB: 5900.09,
-      overrides: {
-        context_window_size: 4096,
-      },
-    },
     // StableLM-zephyr-1.6B
     {
       model: "https://huggingface.co/mlc-ai/stablelm-2-zephyr-1_6b-q4f16_1-MLC",
@@ -1374,6 +1348,61 @@ export const prebuiltAppConfig: AppConfig = {
         context_window_size: 4096,
       },
     },
+    // Qwen2-Math
+    {
+      model:
+        "https://huggingface.co/mlc-ai/Qwen2-Math-1.5B-Instruct-q4f16_1-MLC",
+      model_id: "Qwen2-Math-1.5B-Instruct-q4f16_1-MLC",
+      model_lib:
+        modelLibURLPrefix +
+        modelVersion +
+        "/Qwen2-1.5B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasm",
+      low_resource_required: true,
+      vram_required_MB: 1629.75,
+      overrides: {
+        context_window_size: 4096,
+      },
+    },
+    {
+      model:
+        "https://huggingface.co/mlc-ai/Qwen2-Math-1.5B-Instruct-q4f32_1-MLC",
+      model_id: "Qwen2-Math-1.5B-Instruct-q4f32_1-MLC",
+      model_lib:
+        modelLibURLPrefix +
+        modelVersion +
+        "/Qwen2-1.5B-Instruct-q4f32_1-ctx4k_cs1k-webgpu.wasm",
+      low_resource_required: true,
+      vram_required_MB: 1888.97,
+      overrides: {
+        context_window_size: 4096,
+      },
+    },
+    {
+      model: "https://huggingface.co/mlc-ai/Qwen2-Math-7B-Instruct-q4f16_1-MLC",
+      model_id: "Qwen2-Math-7B-Instruct-q4f16_1-MLC",
+      model_lib:
+        modelLibURLPrefix +
+        modelVersion +
+        "/Qwen2-7B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasm",
+      low_resource_required: false,
+      vram_required_MB: 5106.67,
+      overrides: {
+        context_window_size: 4096,
+      },
+    },
+    {
+      model: "https://huggingface.co/mlc-ai/Qwen2-Math-7B-Instruct-q4f32_1-MLC",
+      model_id: "Qwen2-Math-7B-Instruct-q4f32_1-MLC",
+      model_lib:
+        modelLibURLPrefix +
+        modelVersion +
+        "/Qwen2-7B-Instruct-q4f32_1-ctx4k_cs1k-webgpu.wasm",
+      low_resource_required: false,
+      vram_required_MB: 5900.09,
+      overrides: {
+        context_window_size: 4096,
+      },
+    },
     // Llama-3
     {
       model: "https://huggingface.co/mlc-ai/Llama-3-8B-Instruct-q4f32_1-MLC",