Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,798 @@
+{
+    "architectures": [
+        "Qwen3MoeForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "max_window_layers": 94,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_moe",
+    "moe_intermediate_size": 1536,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 94,
+    "num_key_value_heads": 4,
+    "output_router_logits": false,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.40.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.41.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.42.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.43.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.44.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.45.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.46.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.47.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.48.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.49.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.50.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.51.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.52.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.53.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.54.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.55.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.56.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.57.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.58.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.59.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.60.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.61.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.62.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.63.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.64.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.65.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.66.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.67.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.68.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.69.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.70.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.71.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.72.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.73.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.74.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.75.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.76.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.77.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.78.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.79.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.80.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.81.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.82.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.83.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.84.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.85.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.86.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.87.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.88.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.89.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.90.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.91.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.92.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.93.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.40.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.41.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.42.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.43.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.44.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.45.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.46.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.47.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.48.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.49.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.50.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.51.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.52.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.53.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.54.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.55.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.56.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.57.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.58.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.59.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.60.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.61.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.62.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.63.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.64.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.65.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.66.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.67.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.68.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.69.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.70.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.71.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.72.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.73.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.74.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.75.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.76.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.77.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.78.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.79.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.80.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.81.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.82.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.83.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.84.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.85.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.86.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.87.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.88.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.89.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.90.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.91.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.92.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.93.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 5000000,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.0",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}