Update config.json

config.json

@@ -12,7 +12,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
-  "max_position_embeddings": 140000,
+  "max_position_embeddings": 40960,
   "max_window_layers": 94,
   "mlp_only_layers": [],
   "model_type": "qwen3_moe",
@@ -24,669 +24,20 @@
   "num_hidden_layers": 94,
   "num_key_value_heads": 4,
   "output_router_logits": false,
-  "qkv_bias": false,
-  "quantization_config": {
-    "activation_scheme": "dynamic",
-    "modules_to_not_convert": [
-      "lm_head",
-      "model.layers.0.input_layernorm",
-      "model.layers.0.mlp.gate",
-      "model.layers.0.mlp.shared_expert_gate",
-      "model.layers.0.post_attention_layernorm",
-      "model.layers.0.self_attn.k_proj.bias",
-      "model.layers.0.self_attn.q_proj.bias",
-      "model.layers.0.self_attn.v_proj.bias",
-      "model.layers.1.input_layernorm",
-      "model.layers.1.mlp.gate",
-      "model.layers.1.post_attention_layernorm",
-      "model.layers.1.self_attn.k_proj.bias",
-      "model.layers.1.self_attn.q_proj.bias",
-      "model.layers.1.self_attn.v_proj.bias",
-      "model.layers.1.mlp.shared_expert_gate",
-      "model.layers.2.mlp.shared_expert_gate",
-      "model.layers.2.input_layernorm",
-      "model.layers.2.mlp.gate",
-      "model.layers.2.post_attention_layernorm",
-      "model.layers.2.self_attn.k_proj.bias",
-      "model.layers.2.self_attn.q_proj.bias",
-      "model.layers.2.self_attn.v_proj.bias",
-      "model.layers.3.input_layernorm",
-      "model.layers.3.mlp.gate",
-      "model.layers.3.mlp.shared_expert_gate",
-      "model.layers.3.post_attention_layernorm",
-      "model.layers.3.self_attn.k_proj.bias",
-      "model.layers.3.self_attn.q_proj.bias",
-      "model.layers.3.self_attn.v_proj.bias",
-      "model.layers.4.input_layernorm",
-      "model.layers.4.mlp.gate",
-      "model.layers.4.post_attention_layernorm",
-      "model.layers.4.self_attn.k_proj.bias",
-      "model.layers.4.self_attn.q_proj.bias",
-      "model.layers.4.self_attn.v_proj.bias",
-      "model.layers.4.mlp.shared_expert_gate",
-      "model.layers.5.mlp.shared_expert_gate",
-      "model.layers.5.input_layernorm",
-      "model.layers.5.mlp.gate",
-      "model.layers.5.post_attention_layernorm",
-      "model.layers.5.self_attn.k_proj.bias",
-      "model.layers.5.self_attn.q_proj.bias",
-      "model.layers.5.self_attn.v_proj.bias",
-      "model.layers.6.input_layernorm",
-      "model.layers.6.mlp.gate",
-      "model.layers.6.mlp.shared_expert_gate",
-      "model.layers.6.post_attention_layernorm",
-      "model.layers.6.self_attn.k_proj.bias",
-      "model.layers.6.self_attn.q_proj.bias",
-      "model.layers.6.self_attn.v_proj.bias",
-      "model.layers.7.input_layernorm",
-      "model.layers.7.mlp.gate",
-      "model.layers.7.post_attention_layernorm",
-      "model.layers.7.self_attn.k_proj.bias",
-      "model.layers.7.self_attn.q_proj.bias",
-      "model.layers.7.self_attn.v_proj.bias",
-      "model.layers.7.mlp.shared_expert_gate",
-      "model.layers.8.input_layernorm",
-      "model.layers.8.mlp.gate",
-      "model.layers.8.post_attention_layernorm",
-      "model.layers.8.self_attn.k_proj.bias",
-      "model.layers.8.self_attn.q_proj.bias",
-      "model.layers.8.self_attn.v_proj.bias",
-      "model.layers.8.mlp.shared_expert_gate",
-      "model.layers.9.input_layernorm",
-      "model.layers.9.mlp.gate",
-      "model.layers.9.mlp.shared_expert_gate",
-      "model.layers.9.post_attention_layernorm",
-      "model.layers.9.self_attn.k_proj.bias",
-      "model.layers.9.self_attn.q_proj.bias",
-      "model.layers.9.self_attn.v_proj.bias",
-      "model.layers.10.input_layernorm",
-      "model.layers.10.mlp.gate",
-      "model.layers.10.post_attention_layernorm",
-      "model.layers.10.self_attn.k_proj.bias",
-      "model.layers.10.self_attn.q_proj.bias",
-      "model.layers.10.self_attn.v_proj.bias",
-      "model.layers.10.mlp.shared_expert_gate",
-      "model.layers.11.mlp.shared_expert_gate",
-      "model.layers.11.input_layernorm",
-      "model.layers.11.mlp.gate",
-      "model.layers.11.post_attention_layernorm",
-      "model.layers.11.self_attn.k_proj.bias",
-      "model.layers.11.self_attn.q_proj.bias",
-      "model.layers.11.self_attn.v_proj.bias",
-      "model.layers.12.input_layernorm",
-      "model.layers.12.mlp.gate",
-      "model.layers.12.mlp.shared_expert_gate",
-      "model.layers.12.post_attention_layernorm",
-      "model.layers.12.self_attn.k_proj.bias",
-      "model.layers.12.self_attn.q_proj.bias",
-      "model.layers.12.self_attn.v_proj.bias",
-      "model.layers.13.mlp.shared_expert_gate",
-      "model.layers.13.input_layernorm",
-      "model.layers.13.mlp.gate",
-      "model.layers.13.post_attention_layernorm",
-      "model.layers.13.self_attn.k_proj.bias",
-      "model.layers.13.self_attn.q_proj.bias",
-      "model.layers.13.self_attn.v_proj.bias",
-      "model.layers.14.input_layernorm",
-      "model.layers.14.mlp.gate",
-      "model.layers.14.post_attention_layernorm",
-      "model.layers.14.self_attn.k_proj.bias",
-      "model.layers.14.self_attn.q_proj.bias",
-      "model.layers.14.self_attn.v_proj.bias",
-      "model.layers.14.mlp.shared_expert_gate",
-      "model.layers.15.input_layernorm",
-      "model.layers.15.mlp.gate",
-      "model.layers.15.mlp.shared_expert_gate",
-      "model.layers.15.post_attention_layernorm",
-      "model.layers.15.self_attn.k_proj.bias",
-      "model.layers.15.self_attn.q_proj.bias",
-      "model.layers.15.self_attn.v_proj.bias",
-      "model.layers.16.mlp.shared_expert_gate",
-      "model.layers.16.input_layernorm",
-      "model.layers.16.mlp.gate",
-      "model.layers.16.post_attention_layernorm",
-      "model.layers.16.self_attn.k_proj.bias",
-      "model.layers.16.self_attn.q_proj.bias",
-      "model.layers.16.self_attn.v_proj.bias",
-      "model.layers.17.mlp.shared_expert_gate",
-      "model.layers.17.input_layernorm",
-      "model.layers.17.mlp.gate",
-      "model.layers.17.post_attention_layernorm",
-      "model.layers.17.self_attn.k_proj.bias",
-      "model.layers.17.self_attn.q_proj.bias",
-      "model.layers.17.self_attn.v_proj.bias",
-      "model.layers.18.input_layernorm",
-      "model.layers.18.mlp.gate",
-      "model.layers.18.mlp.shared_expert_gate",
-      "model.layers.18.post_attention_layernorm",
-      "model.layers.18.self_attn.k_proj.bias",
-      "model.layers.18.self_attn.q_proj.bias",
-      "model.layers.18.self_attn.v_proj.bias",
-      "model.layers.19.mlp.shared_expert_gate",
-      "model.layers.19.input_layernorm",
-      "model.layers.19.mlp.gate",
-      "model.layers.19.post_attention_layernorm",
-      "model.layers.19.self_attn.k_proj.bias",
-      "model.layers.19.self_attn.q_proj.bias",
-      "model.layers.19.self_attn.v_proj.bias",
-      "model.layers.20.input_layernorm",
-      "model.layers.20.mlp.gate",
-      "model.layers.20.post_attention_layernorm",
-      "model.layers.20.self_attn.k_proj.bias",
-      "model.layers.20.self_attn.q_proj.bias",
-      "model.layers.20.self_attn.v_proj.bias",
-      "model.layers.20.mlp.shared_expert_gate",
-      "model.layers.21.input_layernorm",
-      "model.layers.21.mlp.gate",
-      "model.layers.21.mlp.shared_expert_gate",
-      "model.layers.21.post_attention_layernorm",
-      "model.layers.21.self_attn.k_proj.bias",
-      "model.layers.21.self_attn.q_proj.bias",
-      "model.layers.21.self_attn.v_proj.bias",
-      "model.layers.22.mlp.shared_expert_gate",
-      "model.layers.22.input_layernorm",
-      "model.layers.22.mlp.gate",
-      "model.layers.22.post_attention_layernorm",
-      "model.layers.22.self_attn.k_proj.bias",
-      "model.layers.22.self_attn.q_proj.bias",
-      "model.layers.22.self_attn.v_proj.bias",
-      "model.layers.23.input_layernorm",
-      "model.layers.23.mlp.gate",
-      "model.layers.23.mlp.shared_expert_gate",
-      "model.layers.23.post_attention_layernorm",
-      "model.layers.23.self_attn.k_proj.bias",
-      "model.layers.23.self_attn.q_proj.bias",
-      "model.layers.23.self_attn.v_proj.bias",
-      "model.layers.24.input_layernorm",
-      "model.layers.24.mlp.gate",
-      "model.layers.24.post_attention_layernorm",
-      "model.layers.24.self_attn.k_proj.bias",
-      "model.layers.24.self_attn.q_proj.bias",
-      "model.layers.24.self_attn.v_proj.bias",
-      "model.layers.24.mlp.shared_expert_gate",
-      "model.layers.25.mlp.shared_expert_gate",
-      "model.layers.25.input_layernorm",
-      "model.layers.25.mlp.gate",
-      "model.layers.25.post_attention_layernorm",
-      "model.layers.25.self_attn.k_proj.bias",
-      "model.layers.25.self_attn.q_proj.bias",
-      "model.layers.25.self_attn.v_proj.bias",
-      "model.layers.26.input_layernorm",
-      "model.layers.26.mlp.gate",
-      "model.layers.26.mlp.shared_expert_gate",
-      "model.layers.26.post_attention_layernorm",
-      "model.layers.26.self_attn.k_proj.bias",
-      "model.layers.26.self_attn.q_proj.bias",
-      "model.layers.26.self_attn.v_proj.bias",
-      "model.layers.27.input_layernorm",
-      "model.layers.27.mlp.gate",
-      "model.layers.27.post_attention_layernorm",
-      "model.layers.27.self_attn.k_proj.bias",
-      "model.layers.27.self_attn.q_proj.bias",
-      "model.layers.27.self_attn.v_proj.bias",
-      "model.layers.27.mlp.shared_expert_gate",
-      "model.layers.28.mlp.shared_expert_gate",
-      "model.layers.28.input_layernorm",
-      "model.layers.28.mlp.gate",
-      "model.layers.28.post_attention_layernorm",
-      "model.layers.28.self_attn.k_proj.bias",
-      "model.layers.28.self_attn.q_proj.bias",
-      "model.layers.28.self_attn.v_proj.bias",
-      "model.layers.29.input_layernorm",
-      "model.layers.29.mlp.gate",
-      "model.layers.29.mlp.shared_expert_gate",
-      "model.layers.29.post_attention_layernorm",
-      "model.layers.29.self_attn.k_proj.bias",
-      "model.layers.29.self_attn.q_proj.bias",
-      "model.layers.29.self_attn.v_proj.bias",
-      "model.layers.30.input_layernorm",
-      "model.layers.30.mlp.gate",
-      "model.layers.30.post_attention_layernorm",
-      "model.layers.30.self_attn.k_proj.bias",
-      "model.layers.30.self_attn.q_proj.bias",
-      "model.layers.30.self_attn.v_proj.bias",
-      "model.layers.30.mlp.shared_expert_gate",
-      "model.layers.31.input_layernorm",
-      "model.layers.31.mlp.gate",
-      "model.layers.31.post_attention_layernorm",
-      "model.layers.31.self_attn.k_proj.bias",
-      "model.layers.31.self_attn.q_proj.bias",
-      "model.layers.31.self_attn.v_proj.bias",
-      "model.layers.31.mlp.shared_expert_gate",
-      "model.layers.32.input_layernorm",
-      "model.layers.32.mlp.gate",
-      "model.layers.32.mlp.shared_expert_gate",
-      "model.layers.32.post_attention_layernorm",
-      "model.layers.32.self_attn.k_proj.bias",
-      "model.layers.32.self_attn.q_proj.bias",
-      "model.layers.32.self_attn.v_proj.bias",
-      "model.layers.33.input_layernorm",
-      "model.layers.33.mlp.gate",
-      "model.layers.33.mlp.shared_expert_gate",
-      "model.layers.33.post_attention_layernorm",
-      "model.layers.33.self_attn.k_proj.bias",
-      "model.layers.33.self_attn.q_proj.bias",
-      "model.layers.33.self_attn.v_proj.bias",
-      "model.layers.34.input_layernorm",
-      "model.layers.34.mlp.gate",
-      "model.layers.34.mlp.shared_expert_gate",
-      "model.layers.34.post_attention_layernorm",
-      "model.layers.34.self_attn.k_proj.bias",
-      "model.layers.34.self_attn.q_proj.bias",
-      "model.layers.34.self_attn.v_proj.bias",
-      "model.layers.35.input_layernorm",
-      "model.layers.35.mlp.gate",
-      "model.layers.35.mlp.shared_expert_gate",
-      "model.layers.35.post_attention_layernorm",
-      "model.layers.35.self_attn.k_proj.bias",
-      "model.layers.35.self_attn.q_proj.bias",
-      "model.layers.35.self_attn.v_proj.bias",
-      "model.layers.36.input_layernorm",
-      "model.layers.36.mlp.gate",
-      "model.layers.36.mlp.shared_expert_gate",
-      "model.layers.36.post_attention_layernorm",
-      "model.layers.36.self_attn.k_proj.bias",
-      "model.layers.36.self_attn.q_proj.bias",
-      "model.layers.36.self_attn.v_proj.bias",
-      "model.layers.37.input_layernorm",
-      "model.layers.37.mlp.gate",
-      "model.layers.37.mlp.shared_expert_gate",
-      "model.layers.37.post_attention_layernorm",
-      "model.layers.37.self_attn.k_proj.bias",
-      "model.layers.37.self_attn.q_proj.bias",
-      "model.layers.37.self_attn.v_proj.bias",
-      "model.layers.38.input_layernorm",
-      "model.layers.38.mlp.gate",
-      "model.layers.38.mlp.shared_expert_gate",
-      "model.layers.38.post_attention_layernorm",
-      "model.layers.38.self_attn.k_proj.bias",
-      "model.layers.38.self_attn.q_proj.bias",
-      "model.layers.38.self_attn.v_proj.bias",
-      "model.layers.39.input_layernorm",
-      "model.layers.39.mlp.gate",
-      "model.layers.39.mlp.shared_expert_gate",
-      "model.layers.39.post_attention_layernorm",
-      "model.layers.39.self_attn.k_proj.bias",
-      "model.layers.39.self_attn.q_proj.bias",
-      "model.layers.39.self_attn.v_proj.bias",
-      "model.layers.40.input_layernorm",
-      "model.layers.40.mlp.gate",
-      "model.layers.40.mlp.shared_expert_gate",
-      "model.layers.40.post_attention_layernorm",
-      "model.layers.40.self_attn.k_proj.bias",
-      "model.layers.40.self_attn.q_proj.bias",
-      "model.layers.40.self_attn.v_proj.bias",
-      "model.layers.41.input_layernorm",
-      "model.layers.41.mlp.gate",
-      "model.layers.41.mlp.shared_expert_gate",
-      "model.layers.41.post_attention_layernorm",
-      "model.layers.41.self_attn.k_proj.bias",
-      "model.layers.41.self_attn.q_proj.bias",
-      "model.layers.41.self_attn.v_proj.bias",
-      "model.layers.42.input_layernorm",
-      "model.layers.42.mlp.gate",
-      "model.layers.42.mlp.shared_expert_gate",
-      "model.layers.42.post_attention_layernorm",
-      "model.layers.42.self_attn.k_proj.bias",
-      "model.layers.42.self_attn.q_proj.bias",
-      "model.layers.42.self_attn.v_proj.bias",
-      "model.layers.43.input_layernorm",
-      "model.layers.43.mlp.gate",
-      "model.layers.43.mlp.shared_expert_gate",
-      "model.layers.43.post_attention_layernorm",
-      "model.layers.43.self_attn.k_proj.bias",
-      "model.layers.43.self_attn.q_proj.bias",
-      "model.layers.43.self_attn.v_proj.bias",
-      "model.layers.44.input_layernorm",
-      "model.layers.44.mlp.gate",
-      "model.layers.44.mlp.shared_expert_gate",
-      "model.layers.44.post_attention_layernorm",
-      "model.layers.44.self_attn.k_proj.bias",
-      "model.layers.44.self_attn.q_proj.bias",
-      "model.layers.44.self_attn.v_proj.bias",
-      "model.layers.45.input_layernorm",
-      "model.layers.45.mlp.gate",
-      "model.layers.45.mlp.shared_expert_gate",
-      "model.layers.45.post_attention_layernorm",
-      "model.layers.45.self_attn.k_proj.bias",
-      "model.layers.45.self_attn.q_proj.bias",
-      "model.layers.45.self_attn.v_proj.bias",
-      "model.layers.46.input_layernorm",
-      "model.layers.46.mlp.gate",
-      "model.layers.46.mlp.shared_expert_gate",
-      "model.layers.46.post_attention_layernorm",
-      "model.layers.46.self_attn.k_proj.bias",
-      "model.layers.46.self_attn.q_proj.bias",
-      "model.layers.46.self_attn.v_proj.bias",
-      "model.layers.47.input_layernorm",
-      "model.layers.47.mlp.gate",
-      "model.layers.47.mlp.shared_expert_gate",
-      "model.layers.47.post_attention_layernorm",
-      "model.layers.47.self_attn.k_proj.bias",
-      "model.layers.47.self_attn.q_proj.bias",
-      "model.layers.47.self_attn.v_proj.bias",
-      "model.layers.48.input_layernorm",
-      "model.layers.48.mlp.gate",
-      "model.layers.48.mlp.shared_expert_gate",
-      "model.layers.48.post_attention_layernorm",
-      "model.layers.48.self_attn.k_proj.bias",
-      "model.layers.48.self_attn.q_proj.bias",
-      "model.layers.48.self_attn.v_proj.bias",
-      "model.layers.49.input_layernorm",
-      "model.layers.49.mlp.gate",
-      "model.layers.49.mlp.shared_expert_gate",
-      "model.layers.49.post_attention_layernorm",
-      "model.layers.49.self_attn.k_proj.bias",
-      "model.layers.49.self_attn.q_proj.bias",
-      "model.layers.49.self_attn.v_proj.bias",
-      "model.layers.50.input_layernorm",
-      "model.layers.50.mlp.gate",
-      "model.layers.50.mlp.shared_expert_gate",
-      "model.layers.50.post_attention_layernorm",
-      "model.layers.50.self_attn.k_proj.bias",
-      "model.layers.50.self_attn.q_proj.bias",
-      "model.layers.50.self_attn.v_proj.bias",
-      "model.layers.51.input_layernorm",
-      "model.layers.51.mlp.gate",
-      "model.layers.51.mlp.shared_expert_gate",
-      "model.layers.51.post_attention_layernorm",
-      "model.layers.51.self_attn.k_proj.bias",
-      "model.layers.51.self_attn.q_proj.bias",
-      "model.layers.51.self_attn.v_proj.bias",
-      "model.layers.52.input_layernorm",
-      "model.layers.52.mlp.gate",
-      "model.layers.52.mlp.shared_expert_gate",
-      "model.layers.52.post_attention_layernorm",
-      "model.layers.52.self_attn.k_proj.bias",
-      "model.layers.52.self_attn.q_proj.bias",
-      "model.layers.52.self_attn.v_proj.bias",
-      "model.layers.53.input_layernorm",
-      "model.layers.53.mlp.gate",
-      "model.layers.53.mlp.shared_expert_gate",
-      "model.layers.53.post_attention_layernorm",
-      "model.layers.53.self_attn.k_proj.bias",
-      "model.layers.53.self_attn.q_proj.bias",
-      "model.layers.53.self_attn.v_proj.bias",
-      "model.layers.54.input_layernorm",
-      "model.layers.54.mlp.gate",
-      "model.layers.54.mlp.shared_expert_gate",
-      "model.layers.54.post_attention_layernorm",
-      "model.layers.54.self_attn.k_proj.bias",
-      "model.layers.54.self_attn.q_proj.bias",
-      "model.layers.54.self_attn.v_proj.bias",
-      "model.layers.55.input_layernorm",
-      "model.layers.55.mlp.gate",
-      "model.layers.55.mlp.shared_expert_gate",
-      "model.layers.55.post_attention_layernorm",
-      "model.layers.55.self_attn.k_proj.bias",
-      "model.layers.55.self_attn.q_proj.bias",
-      "model.layers.55.self_attn.v_proj.bias",
-      "model.layers.56.input_layernorm",
-      "model.layers.56.mlp.gate",
-      "model.layers.56.mlp.shared_expert_gate",
-      "model.layers.56.post_attention_layernorm",
-      "model.layers.56.self_attn.k_proj.bias",
-      "model.layers.56.self_attn.q_proj.bias",
-      "model.layers.56.self_attn.v_proj.bias",
-      "model.layers.57.input_layernorm",
-      "model.layers.57.mlp.gate",
-      "model.layers.57.mlp.shared_expert_gate",
-      "model.layers.57.post_attention_layernorm",
-      "model.layers.57.self_attn.k_proj.bias",
-      "model.layers.57.self_attn.q_proj.bias",
-      "model.layers.57.self_attn.v_proj.bias",
-      "model.layers.58.input_layernorm",
-      "model.layers.58.mlp.gate",
-      "model.layers.58.mlp.shared_expert_gate",
-      "model.layers.58.post_attention_layernorm",
-      "model.layers.58.self_attn.k_proj.bias",
-      "model.layers.58.self_attn.q_proj.bias",
-      "model.layers.58.self_attn.v_proj.bias",
-      "model.layers.59.input_layernorm",
-      "model.layers.59.mlp.gate",
-      "model.layers.59.mlp.shared_expert_gate",
-      "model.layers.59.post_attention_layernorm",
-      "model.layers.59.self_attn.k_proj.bias",
-      "model.layers.59.self_attn.q_proj.bias",
-      "model.layers.59.self_attn.v_proj.bias",
-      "model.layers.60.input_layernorm",
-      "model.layers.60.mlp.gate",
-      "model.layers.60.mlp.shared_expert_gate",
-      "model.layers.60.post_attention_layernorm",
-      "model.layers.60.self_attn.k_proj.bias",
-      "model.layers.60.self_attn.q_proj.bias",
-      "model.layers.60.self_attn.v_proj.bias",
-      "model.layers.61.input_layernorm",
-      "model.layers.61.mlp.gate",
-      "model.layers.61.mlp.shared_expert_gate",
-      "model.layers.61.post_attention_layernorm",
-      "model.layers.61.self_attn.k_proj.bias",
-      "model.layers.61.self_attn.q_proj.bias",
-      "model.layers.61.self_attn.v_proj.bias",
-      "model.layers.62.input_layernorm",
-      "model.layers.62.mlp.gate",
-      "model.layers.62.mlp.shared_expert_gate",
-      "model.layers.62.post_attention_layernorm",
-      "model.layers.62.self_attn.k_proj.bias",
-      "model.layers.62.self_attn.q_proj.bias",
-      "model.layers.62.self_attn.v_proj.bias",
-      "model.layers.63.input_layernorm",
-      "model.layers.63.mlp.gate",
-      "model.layers.63.mlp.shared_expert_gate",
-      "model.layers.63.post_attention_layernorm",
-      "model.layers.63.self_attn.k_proj.bias",
-      "model.layers.63.self_attn.q_proj.bias",
-      "model.layers.63.self_attn.v_proj.bias",
-      "model.layers.64.input_layernorm",
-      "model.layers.64.mlp.gate",
-      "model.layers.64.mlp.shared_expert_gate",
-      "model.layers.64.post_attention_layernorm",
-      "model.layers.64.self_attn.k_proj.bias",
-      "model.layers.64.self_attn.q_proj.bias",
-      "model.layers.64.self_attn.v_proj.bias",
-      "model.layers.65.input_layernorm",
-      "model.layers.65.mlp.gate",
-      "model.layers.65.mlp.shared_expert_gate",
-      "model.layers.65.post_attention_layernorm",
-      "model.layers.65.self_attn.k_proj.bias",
-      "model.layers.65.self_attn.q_proj.bias",
-      "model.layers.65.self_attn.v_proj.bias",
-      "model.layers.66.input_layernorm",
-      "model.layers.66.mlp.gate",
-      "model.layers.66.mlp.shared_expert_gate",
-      "model.layers.66.post_attention_layernorm",
-      "model.layers.66.self_attn.k_proj.bias",
-      "model.layers.66.self_attn.q_proj.bias",
-      "model.layers.66.self_attn.v_proj.bias",
-      "model.layers.67.input_layernorm",
-      "model.layers.67.mlp.gate",
-      "model.layers.67.mlp.shared_expert_gate",
-      "model.layers.67.post_attention_layernorm",
-      "model.layers.67.self_attn.k_proj.bias",
-      "model.layers.67.self_attn.q_proj.bias",
-      "model.layers.67.self_attn.v_proj.bias",
-      "model.layers.68.input_layernorm",
-      "model.layers.68.mlp.gate",
-      "model.layers.68.mlp.shared_expert_gate",
-      "model.layers.68.post_attention_layernorm",
-      "model.layers.68.self_attn.k_proj.bias",
-      "model.layers.68.self_attn.q_proj.bias",
-      "model.layers.68.self_attn.v_proj.bias",
-      "model.layers.69.input_layernorm",
-      "model.layers.69.mlp.gate",
-      "model.layers.69.mlp.shared_expert_gate",
-      "model.layers.69.post_attention_layernorm",
-      "model.layers.69.self_attn.k_proj.bias",
-      "model.layers.69.self_attn.q_proj.bias",
-      "model.layers.69.self_attn.v_proj.bias",
-      "model.layers.70.input_layernorm",
-      "model.layers.70.mlp.gate",
-      "model.layers.70.mlp.shared_expert_gate",
-      "model.layers.70.post_attention_layernorm",
-      "model.layers.70.self_attn.k_proj.bias",
-      "model.layers.70.self_attn.q_proj.bias",
-      "model.layers.70.self_attn.v_proj.bias",
-      "model.layers.71.input_layernorm",
-      "model.layers.71.mlp.gate",
-      "model.layers.71.mlp.shared_expert_gate",
-      "model.layers.71.post_attention_layernorm",
-      "model.layers.71.self_attn.k_proj.bias",
-      "model.layers.71.self_attn.q_proj.bias",
-      "model.layers.71.self_attn.v_proj.bias",
-      "model.layers.72.input_layernorm",
-      "model.layers.72.mlp.gate",
-      "model.layers.72.mlp.shared_expert_gate",
-      "model.layers.72.post_attention_layernorm",
-      "model.layers.72.self_attn.k_proj.bias",
-      "model.layers.72.self_attn.q_proj.bias",
-      "model.layers.72.self_attn.v_proj.bias",
-      "model.layers.73.input_layernorm",
-      "model.layers.73.mlp.gate",
-      "model.layers.73.mlp.shared_expert_gate",
-      "model.layers.73.post_attention_layernorm",
-      "model.layers.73.self_attn.k_proj.bias",
-      "model.layers.73.self_attn.q_proj.bias",
-      "model.layers.73.self_attn.v_proj.bias",
-      "model.layers.74.input_layernorm",
-      "model.layers.74.mlp.gate",
-      "model.layers.74.mlp.shared_expert_gate",
-      "model.layers.74.post_attention_layernorm",
-      "model.layers.74.self_attn.k_proj.bias",
-      "model.layers.74.self_attn.q_proj.bias",
-      "model.layers.74.self_attn.v_proj.bias",
-      "model.layers.75.input_layernorm",
-      "model.layers.75.mlp.gate",
-      "model.layers.75.mlp.shared_expert_gate",
-      "model.layers.75.post_attention_layernorm",
-      "model.layers.75.self_attn.k_proj.bias",
-      "model.layers.75.self_attn.q_proj.bias",
-      "model.layers.75.self_attn.v_proj.bias",
-      "model.layers.76.input_layernorm",
-      "model.layers.76.mlp.gate",
-      "model.layers.76.mlp.shared_expert_gate",
-      "model.layers.76.post_attention_layernorm",
-      "model.layers.76.self_attn.k_proj.bias",
-      "model.layers.76.self_attn.q_proj.bias",
-      "model.layers.76.self_attn.v_proj.bias",
-      "model.layers.77.input_layernorm",
-      "model.layers.77.mlp.gate",
-      "model.layers.77.mlp.shared_expert_gate",
-      "model.layers.77.post_attention_layernorm",
-      "model.layers.77.self_attn.k_proj.bias",
-      "model.layers.77.self_attn.q_proj.bias",
-      "model.layers.77.self_attn.v_proj.bias",
-      "model.layers.78.input_layernorm",
-      "model.layers.78.mlp.gate",
-      "model.layers.78.mlp.shared_expert_gate",
-      "model.layers.78.post_attention_layernorm",
-      "model.layers.78.self_attn.k_proj.bias",
-      "model.layers.78.self_attn.q_proj.bias",
-      "model.layers.78.self_attn.v_proj.bias",
-      "model.layers.79.input_layernorm",
-      "model.layers.79.mlp.gate",
-      "model.layers.79.mlp.shared_expert_gate",
-      "model.layers.79.post_attention_layernorm",
-      "model.layers.79.self_attn.k_proj.bias",
-      "model.layers.79.self_attn.q_proj.bias",
-      "model.layers.79.self_attn.v_proj.bias",
-      "model.layers.80.input_layernorm",
-      "model.layers.80.mlp.gate",
-      "model.layers.80.mlp.shared_expert_gate",
-      "model.layers.80.post_attention_layernorm",
-      "model.layers.80.self_attn.k_proj.bias",
-      "model.layers.80.self_attn.q_proj.bias",
-      "model.layers.80.self_attn.v_proj.bias",
-      "model.layers.81.input_layernorm",
-      "model.layers.81.mlp.gate",
-      "model.layers.81.mlp.shared_expert_gate",
-      "model.layers.81.post_attention_layernorm",
-      "model.layers.81.self_attn.k_proj.bias",
-      "model.layers.81.self_attn.q_proj.bias",
-      "model.layers.81.self_attn.v_proj.bias",
-      "model.layers.82.input_layernorm",
-      "model.layers.82.mlp.gate",
-      "model.layers.82.mlp.shared_expert_gate",
-      "model.layers.82.post_attention_layernorm",
-      "model.layers.82.self_attn.k_proj.bias",
-      "model.layers.82.self_attn.q_proj.bias",
-      "model.layers.82.self_attn.v_proj.bias",
-      "model.layers.83.input_layernorm",
-      "model.layers.83.mlp.gate",
-      "model.layers.83.mlp.shared_expert_gate",
-      "model.layers.83.post_attention_layernorm",
-      "model.layers.83.self_attn.k_proj.bias",
-      "model.layers.83.self_attn.q_proj.bias",
-      "model.layers.83.self_attn.v_proj.bias",
-      "model.layers.84.input_layernorm",
-      "model.layers.84.mlp.gate",
-      "model.layers.84.mlp.shared_expert_gate",
-      "model.layers.84.post_attention_layernorm",
-      "model.layers.84.self_attn.k_proj.bias",
-      "model.layers.84.self_attn.q_proj.bias",
-      "model.layers.84.self_attn.v_proj.bias",
-      "model.layers.85.input_layernorm",
-      "model.layers.85.mlp.gate",
-      "model.layers.85.mlp.shared_expert_gate",
-      "model.layers.85.post_attention_layernorm",
-      "model.layers.85.self_attn.k_proj.bias",
-      "model.layers.85.self_attn.q_proj.bias",
-      "model.layers.85.self_attn.v_proj.bias",
-      "model.layers.86.input_layernorm",
-      "model.layers.86.mlp.gate",
-      "model.layers.86.mlp.shared_expert_gate",
-      "model.layers.86.post_attention_layernorm",
-      "model.layers.86.self_attn.k_proj.bias",
-      "model.layers.86.self_attn.q_proj.bias",
-      "model.layers.86.self_attn.v_proj.bias",
-      "model.layers.87.input_layernorm",
-      "model.layers.87.mlp.gate",
-      "model.layers.87.mlp.shared_expert_gate",
-      "model.layers.87.post_attention_layernorm",
-      "model.layers.87.self_attn.k_proj.bias",
-      "model.layers.87.self_attn.q_proj.bias",
-      "model.layers.87.self_attn.v_proj.bias",
-      "model.layers.88.input_layernorm",
-      "model.layers.88.mlp.gate",
-      "model.layers.88.mlp.shared_expert_gate",
-      "model.layers.88.post_attention_layernorm",
-      "model.layers.88.self_attn.k_proj.bias",
-      "model.layers.88.self_attn.q_proj.bias",
-      "model.layers.88.self_attn.v_proj.bias",
-      "model.layers.89.input_layernorm",
-      "model.layers.89.mlp.gate",
-      "model.layers.89.mlp.shared_expert_gate",
-      "model.layers.89.post_attention_layernorm",
-      "model.layers.89.self_attn.k_proj.bias",
-      "model.layers.89.self_attn.q_proj.bias",
-      "model.layers.89.self_attn.v_proj.bias",
-      "model.layers.90.input_layernorm",
-      "model.layers.90.mlp.gate",
-      "model.layers.90.mlp.shared_expert_gate",
-      "model.layers.90.post_attention_layernorm",
-      "model.layers.90.self_attn.k_proj.bias",
-      "model.layers.90.self_attn.q_proj.bias",
-      "model.layers.90.self_attn.v_proj.bias",
-      "model.layers.91.input_layernorm",
-      "model.layers.91.mlp.gate",
-      "model.layers.91.mlp.shared_expert_gate",
-      "model.layers.91.post_attention_layernorm",
-      "model.layers.91.self_attn.k_proj.bias",
-      "model.layers.91.self_attn.q_proj.bias",
-      "model.layers.91.self_attn.v_proj.bias",
-      "model.layers.92.input_layernorm",
-      "model.layers.92.mlp.gate",
-      "model.layers.92.mlp.shared_expert_gate",
-      "model.layers.92.post_attention_layernorm",
-      "model.layers.92.self_attn.k_proj.bias",
-      "model.layers.92.self_attn.q_proj.bias",
-      "model.layers.92.self_attn.v_proj.bias",
-      "model.layers.93.input_layernorm",
-      "model.layers.93.mlp.gate",
-      "model.layers.93.mlp.shared_expert_gate",
-      "model.layers.93.post_attention_layernorm",
-      "model.layers.93.self_attn.k_proj.bias",
-      "model.layers.93.self_attn.q_proj.bias",
-      "model.layers.93.self_attn.v_proj.bias",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "modules_to_not_convert": [
       "lm_head",
       "model.layers.0.input_layernorm",
       "model.layers.0.mlp.gate",
@@ -1347,23 +698,11 @@
       "model.layers.93.self_attn.q_proj.bias",
       "model.layers.93.self_attn.v_proj.bias"
     ],
+    "fmt": "e4m3",
     "quant_method": "fp8",
     "weight_block_size": [
       128,
       128
     ]
-  },
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "router_aux_loss_coef": 0.001,
-  "shared_expert_intermediate_size": 0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.51.0",
-  "use_cache": true,
-  "use_qk_norm": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}
+  }
+}