初始化项目，由ModelHub XC社区提供模型

Model: QuantTrio/Qwen3-VL-30B-A3B-Thinking-AWQ Source: Original Platform
2026-10-19 22:32:13 +08:00
commit ab95a67e24
19 changed files with 698 additions and 0 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,81 @@
+{
+  "name_or_path": "tclf90/Qwen3-VL-30B-A3B-Thinking-AWQ",
+  "architectures": [
+    "Qwen3VLMoeForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl_moe",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_vl_moe_text",
+    "moe_intermediate_size": 768,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl_moe",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "torch_dtype": "float16",
+  "quantization_config": {
+    "quant_method": "awq",
+    "bits": 4,
+    "group_size": 128,
+    "version": "gemm",
+    "zero_point": true,
+    "modules_to_not_convert": [
+      "visual",
+      "mlp.gate"
+    ]
+  }
+}