初始化项目，由ModelHub XC社区提供模型

Model: neuralmagic/Llama-2-7b-chat-quantized.w8a8 Source: Original Platform
2026-05-22 08:32:12 +08:00
commit 8dcdeaee87
13 changed files with 98181 additions and 0 deletions
--- a/recipe.yaml
+++ b/recipe.yaml
@@ -0,0 +1,11 @@
+quant_stage:
+  quant_modifiers:
+    GPTQModifier:
+      sequential_update: false
+      dampening_frac: 1
+      ignore: [lm_head]
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights: {num_bits: 8, type: int, symmetric: true, strategy: channel}
+          input_activations: {num_bits: 8, type: int, symmetric: true, dynamic: true, strategy: token}