Upload config.json with huggingface_hub

config.json

@@ -1,605 +1,606 @@
 {
-    "architectures": [
-        "MiniMaxM2ForCausalLM"
-    ],
-    "attn_type_list": [
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1,
-        1
-    ],
-    "auto_map": {
-        "AutoConfig": "configuration_minimax_m2.MiniMaxM2Config",
-        "AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM"
-    },
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 3072,
-    "intermediate_size": 1536,
-    "max_position_embeddings": 196608,
-    "model_type": "minimax_m2",
-    "mtp_transformer_layers": 1,
-    "num_attention_heads": 48,
-    "num_experts_per_tok": 8,
-    "num_hidden_layers": 62,
-    "num_key_value_heads": 8,
-    "num_local_experts": 192,
-    "num_mtp_modules": 3,
-    "qk_norm_type": "per_layer",
-    "quantization": {
-        "group_size": 64,
-        "bits": 6,
-        "mode": "affine",
-        "model.layers.0.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.1.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.2.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.3.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.4.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.5.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.6.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.7.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.8.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.9.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.10.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.11.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.12.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.13.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.14.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.15.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.16.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.17.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.18.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.19.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.20.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.21.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.22.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.23.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.24.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.25.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.26.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.27.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.28.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.29.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.30.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.31.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.32.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.33.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.34.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.35.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.36.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.37.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.38.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.39.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.40.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.41.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.42.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.43.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.44.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.45.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.46.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.47.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.48.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.49.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.50.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.51.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.52.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.53.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.54.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.55.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.56.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.57.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.58.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.59.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.60.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.61.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        }
-    },
-    "quantization_config": {
-        "group_size": 64,
-        "bits": 6,
-        "mode": "affine",
-        "model.layers.0.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.1.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.2.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.3.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.4.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.5.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.6.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.7.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.8.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.9.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.10.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.11.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.12.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.13.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.14.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.15.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.16.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.17.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.18.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.19.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.20.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.21.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.22.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.23.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.24.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.25.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.26.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.27.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.28.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.29.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.30.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.31.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.32.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.33.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.34.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.35.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.36.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.37.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.38.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.39.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.40.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.41.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.42.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.43.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.44.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.45.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.46.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.47.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.48.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.49.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.50.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.51.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.52.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.53.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.54.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.55.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.56.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.57.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.58.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.59.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.60.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "model.layers.61.block_sparse_moe.gate": {
-            "group_size": 64,
-            "bits": 8
-        }
-    },
-    "rms_norm_eps": 1e-06,
-    "rope_theta": 5000000,
-    "rotary_dim": 64,
-    "scoring_func": "sigmoid",
-    "shared_intermediate_size": 0,
-    "tie_word_embeddings": false,
-    "transformers_version": "4.46.1",
-    "use_cache": true,
-    "use_mtp": true,
-    "use_qk_norm": true,
-    "use_routing_bias": true,
-    "vocab_size": 200064
+  "architectures": [
+    "MiniMaxM2ForCausalLM"
+  ],
+  "attn_type_list": [
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_minimax_m2.MiniMaxM2Config",
+    "AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM"
+  },
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 196608,
+  "model_type": "minimax_m2",
+  "mtp_transformer_layers": 1,
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "num_local_experts": 192,
+  "num_mtp_modules": 3,
+  "qk_norm_type": "per_layer",
+  "quantization": {
+    "group_size": 64,
+    "bits": 6,
+    "mode": "affine",
+    "model.layers.0.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.1.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.2.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.3.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.4.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.5.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.6.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.7.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.8.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.9.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.10.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.11.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.12.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.13.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.14.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.15.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.16.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.17.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.18.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.19.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.20.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.21.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.22.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.23.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.24.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.25.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.26.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.27.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.28.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.29.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.30.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.31.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.32.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.33.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.34.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.35.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.36.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.37.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.38.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.39.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.40.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.41.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.42.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.43.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.44.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.45.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.46.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.47.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.48.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.49.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.50.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.51.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.52.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.53.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.54.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.55.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.56.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.57.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.58.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.59.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.60.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.61.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    }
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 6,
+    "mode": "affine",
+    "model.layers.0.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.1.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.2.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.3.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.4.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.5.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.6.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.7.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.8.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.9.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.10.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.11.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.12.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.13.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.14.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.15.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.16.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.17.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.18.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.19.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.20.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.21.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.22.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.23.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.24.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.25.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.26.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.27.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.28.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.29.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.30.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.31.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.32.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.33.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.34.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.35.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.36.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.37.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.38.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.39.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.40.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.41.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.42.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.43.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.44.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.45.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.46.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.47.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.48.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.49.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.50.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.51.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.52.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.53.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.54.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.55.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.56.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.57.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.58.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.59.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.60.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "model.layers.61.block_sparse_moe.gate": {
+      "group_size": 64,
+      "bits": 8
+    }
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 5000000,
+  "rotary_dim": 64,
+  "scoring_func": "sigmoid",
+  "shared_intermediate_size": 0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_mtp": true,
+  "use_qk_norm": true,
+  "use_routing_bias": true,
+  "vocab_size": 200064,
+  "eos_token_id": 200020
 }