初始化项目，由ModelHub XC社区提供模型

Model: ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-w4a16 Source: Original Platform
2026-08-11 19:59:13 +08:00
commit c066424ddd
15 changed files with 775 additions and 0 deletions
--- a/quantize_config.json
+++ b/quantize_config.json
@@ -0,0 +1,25 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "desc_act": false,
+  "sym": true,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:5.0.0-dev0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.05,
+    "damp_auto_increment": 0.01,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "v2": false,
+    "v2_alpha": 0.25,
+    "act_group_aware": true
+  },
+  "pack_impl": "cpu"
+}