Align tiny-Glm4MoeForCausalLM with GLM-4.5 reference config

scripts/generate_tiny_models/for_causal_lm/glm4_moe_for_causal_lm.py

@@ -32,14 +32,23 @@
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 generation_config = GenerationConfig.from_pretrained(MODEL_ID)
 config = Glm4MoeConfig(
-    vocab_size=len(tokenizer.vocab),
+    vocab_size=151365,
     hidden_size=8,
     num_attention_heads=4,
     num_key_value_heads=2,
     num_hidden_layers=2,
     intermediate_size=32,
+    moe_intermediate_size=32,
+    head_dim=2,
     n_routed_experts=4,
     num_experts_per_tok=2,
+    attention_bias=True,
+    eos_token_id=[151329, 151336, 151338],
+    pad_token_id=151329,
+    rope_theta=1000000,
+    routed_scaling_factor=2.5,
+    use_qk_norm=True,
+    num_nextn_predict_layers=1,
 )
 model = Glm4MoeForCausalLM(config).to(dtype=torch.bfloat16)
 init_weights_tiny_model(model)