Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,58 @@
+{
+    "architectures": [
+        "Glm4MoeForCausalLM"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_glm4_moe.Glm4MoeConfig",
+        "AutoModel": "modeling_glm4_moe.Glm4MoeModel",
+        "AutoModelForCausalLM": "modeling_glm4_moe.Glm4MoeForCausalLM"
+    },
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        151334,
+        151329
+    ],
+    "first_k_dense_replace": 1,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 10944,
+    "max_position_embeddings": 131072,
+    "model_type": "glm4_moe",
+    "moe_intermediate_size": 1408,
+    "n_group": 1,
+    "n_routed_experts": 128,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 96,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 46,
+    "num_key_value_heads": 8,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 151329,
+    "partial_rotary_factor": 0.5,
+    "quantization": {
+        "group_size": 64,
+        "bits": 5,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 5,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "routed_scaling_factor": 1.0,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "transformers_version": "4.56.1",
+    "use_cache": false,
+    "use_grouped_mm": true,
+    "use_qk_norm": false,
+    "vocab_size": 151552
+}