Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,330 @@
+{
+    "architectures": [
+        "AfmoeForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_afmoe.AfmoeConfig",
+        "AutoModel": "modeling_afmoe.AfmoeModel",
+        "AutoModelForCausalLM": "modeling_afmoe.AfmoeForCausalLM"
+    },
+    "dtype": "bfloat16",
+    "global_attn_every_n_layers": 4,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention"
+    ],
+    "load_balance_coeff": 0.001,
+    "max_position_embeddings": 131072,
+    "model_type": "afmoe",
+    "moe_intermediate_size": 1024,
+    "mup_enabled": true,
+    "n_group": 1,
+    "num_attention_heads": 32,
+    "num_dense_layers": 2,
+    "num_expert_groups": 1,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "num_limited_groups": 1,
+    "num_shared_experts": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine",
+        "model.layers.2.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine",
+        "model.layers.2.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000,
+    "route_norm": true,
+    "route_scale": 2.826,
+    "score_func": "sigmoid",
+    "sliding_window": 2048,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "transformers_version": "4.57.3",
+    "use_cache": true,
+    "use_grouped_mm": true,
+    "vocab_size": 200192
+}