初始化项目，由ModelHub XC社区提供模型

Model: 0xSero/GLM-4.7-REAP-50-W4A16
Source: Original Platform

config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "first_k_dense_replace": 3,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 202752,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1536,
+  "n_group": 1,
+  "n_routed_experts": 80,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 92,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "quantization_config": {
+    "autoround_version": "0.9.4",
+    "bits": 4,
+    "damp_percent": 0.01,
+    "data_type": "int",
+    "desc_act": false,
+    "group_size": 128,
+    "lm_head": false,
+    "provider": "auto-round",
+    "quant_method": "gptq",
+    "sym": true,
+    "true_sequential": false
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 2.5,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_qk_norm": true,
+  "vocab_size": 151552,
+  "torch_dtype": "float16"
+}