cpatonn's picture
Upload folder using huggingface_hub
7dfa80b verified
{
"architectures": [
"Qwen3VLMoeForConditionalGeneration"
],
"dtype": "bfloat16",
"image_token_id": 151655,
"model_type": "qwen3_vl_moe",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "pack-quantized",
"input_activations": null,
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": 32,
"num_bits": 8,
"observer": "mse",
"observer_kwargs": {},
"strategy": "group",
"symmetric": true,
"type": "int"
}
}
},
"format": "pack-quantized",
"global_compression_ratio": null,
"ignore": [
"model.visual.blocks.0.attn.qkv",
"model.visual.blocks.0.attn.proj",
"model.visual.blocks.0.mlp.linear_fc1",
"model.visual.blocks.0.mlp.linear_fc2",
"model.visual.blocks.1.attn.qkv",
"model.visual.blocks.1.attn.proj",
"model.visual.blocks.1.mlp.linear_fc1",
"model.visual.blocks.1.mlp.linear_fc2",
"model.visual.blocks.2.attn.qkv",
"model.visual.blocks.2.attn.proj",
"model.visual.blocks.2.mlp.linear_fc1",
"model.visual.blocks.2.mlp.linear_fc2",
"model.visual.blocks.3.attn.qkv",
"model.visual.blocks.3.attn.proj",
"model.visual.blocks.3.mlp.linear_fc1",
"model.visual.blocks.3.mlp.linear_fc2",
"model.visual.blocks.4.attn.qkv",
"model.visual.blocks.4.attn.proj",
"model.visual.blocks.4.mlp.linear_fc1",
"model.visual.blocks.4.mlp.linear_fc2",
"model.visual.blocks.5.attn.qkv",
"model.visual.blocks.5.attn.proj",
"model.visual.blocks.5.mlp.linear_fc1",
"model.visual.blocks.5.mlp.linear_fc2",
"model.visual.blocks.6.attn.qkv",
"model.visual.blocks.6.attn.proj",
"model.visual.blocks.6.mlp.linear_fc1",
"model.visual.blocks.6.mlp.linear_fc2",
"model.visual.blocks.7.attn.qkv",
"model.visual.blocks.7.attn.proj",
"model.visual.blocks.7.mlp.linear_fc1",
"model.visual.blocks.7.mlp.linear_fc2",
"model.visual.blocks.8.attn.qkv",
"model.visual.blocks.8.attn.proj",
"model.visual.blocks.8.mlp.linear_fc1",
"model.visual.blocks.8.mlp.linear_fc2",
"model.visual.blocks.9.attn.qkv",
"model.visual.blocks.9.attn.proj",
"model.visual.blocks.9.mlp.linear_fc1",
"model.visual.blocks.9.mlp.linear_fc2",
"model.visual.blocks.10.attn.qkv",
"model.visual.blocks.10.attn.proj",
"model.visual.blocks.10.mlp.linear_fc1",
"model.visual.blocks.10.mlp.linear_fc2",
"model.visual.blocks.11.attn.qkv",
"model.visual.blocks.11.attn.proj",
"model.visual.blocks.11.mlp.linear_fc1",
"model.visual.blocks.11.mlp.linear_fc2",
"model.visual.blocks.12.attn.qkv",
"model.visual.blocks.12.attn.proj",
"model.visual.blocks.12.mlp.linear_fc1",
"model.visual.blocks.12.mlp.linear_fc2",
"model.visual.blocks.13.attn.qkv",
"model.visual.blocks.13.attn.proj",
"model.visual.blocks.13.mlp.linear_fc1",
"model.visual.blocks.13.mlp.linear_fc2",
"model.visual.blocks.14.attn.qkv",
"model.visual.blocks.14.attn.proj",
"model.visual.blocks.14.mlp.linear_fc1",
"model.visual.blocks.14.mlp.linear_fc2",
"model.visual.blocks.15.attn.qkv",
"model.visual.blocks.15.attn.proj",
"model.visual.blocks.15.mlp.linear_fc1",
"model.visual.blocks.15.mlp.linear_fc2",
"model.visual.blocks.16.attn.qkv",
"model.visual.blocks.16.attn.proj",
"model.visual.blocks.16.mlp.linear_fc1",
"model.visual.blocks.16.mlp.linear_fc2",
"model.visual.blocks.17.attn.qkv",
"model.visual.blocks.17.attn.proj",
"model.visual.blocks.17.mlp.linear_fc1",
"model.visual.blocks.17.mlp.linear_fc2",
"model.visual.blocks.18.attn.qkv",
"model.visual.blocks.18.attn.proj",
"model.visual.blocks.18.mlp.linear_fc1",
"model.visual.blocks.18.mlp.linear_fc2",
"model.visual.blocks.19.attn.qkv",
"model.visual.blocks.19.attn.proj",
"model.visual.blocks.19.mlp.linear_fc1",
"model.visual.blocks.19.mlp.linear_fc2",
"model.visual.blocks.20.attn.qkv",
"model.visual.blocks.20.attn.proj",
"model.visual.blocks.20.mlp.linear_fc1",
"model.visual.blocks.20.mlp.linear_fc2",
"model.visual.blocks.21.attn.qkv",
"model.visual.blocks.21.attn.proj",
"model.visual.blocks.21.mlp.linear_fc1",
"model.visual.blocks.21.mlp.linear_fc2",
"model.visual.blocks.22.attn.qkv",
"model.visual.blocks.22.attn.proj",
"model.visual.blocks.22.mlp.linear_fc1",
"model.visual.blocks.22.mlp.linear_fc2",
"model.visual.blocks.23.attn.qkv",
"model.visual.blocks.23.attn.proj",
"model.visual.blocks.23.mlp.linear_fc1",
"model.visual.blocks.23.mlp.linear_fc2",
"model.visual.blocks.24.attn.qkv",
"model.visual.blocks.24.attn.proj",
"model.visual.blocks.24.mlp.linear_fc1",
"model.visual.blocks.24.mlp.linear_fc2",
"model.visual.blocks.25.attn.qkv",
"model.visual.blocks.25.attn.proj",
"model.visual.blocks.25.mlp.linear_fc1",
"model.visual.blocks.25.mlp.linear_fc2",
"model.visual.blocks.26.attn.qkv",
"model.visual.blocks.26.attn.proj",
"model.visual.blocks.26.mlp.linear_fc1",
"model.visual.blocks.26.mlp.linear_fc2",
"model.visual.merger.linear_fc1",
"model.visual.merger.linear_fc2",
"model.visual.deepstack_merger_list.0.linear_fc1",
"model.visual.deepstack_merger_list.0.linear_fc2",
"model.visual.deepstack_merger_list.1.linear_fc1",
"model.visual.deepstack_merger_list.1.linear_fc2",
"model.visual.deepstack_merger_list.2.linear_fc1",
"model.visual.deepstack_merger_list.2.linear_fc2",
"model.language_model.layers.0.mlp.gate",
"model.language_model.layers.1.mlp.gate",
"model.language_model.layers.2.mlp.gate",
"model.language_model.layers.3.mlp.gate",
"model.language_model.layers.4.mlp.gate",
"model.language_model.layers.5.mlp.gate",
"model.language_model.layers.6.mlp.gate",
"model.language_model.layers.7.mlp.gate",
"model.language_model.layers.8.mlp.gate",
"model.language_model.layers.9.mlp.gate",
"model.language_model.layers.10.mlp.gate",
"model.language_model.layers.11.mlp.gate",
"model.language_model.layers.12.mlp.gate",
"model.language_model.layers.13.mlp.gate",
"model.language_model.layers.14.mlp.gate",
"model.language_model.layers.15.mlp.gate",
"model.language_model.layers.16.mlp.gate",
"model.language_model.layers.17.mlp.gate",
"model.language_model.layers.18.mlp.gate",
"model.language_model.layers.19.mlp.gate",
"model.language_model.layers.20.mlp.gate",
"model.language_model.layers.21.mlp.gate",
"model.language_model.layers.22.mlp.gate",
"model.language_model.layers.23.mlp.gate",
"model.language_model.layers.24.mlp.gate",
"model.language_model.layers.25.mlp.gate",
"model.language_model.layers.26.mlp.gate",
"model.language_model.layers.27.mlp.gate",
"model.language_model.layers.28.mlp.gate",
"model.language_model.layers.29.mlp.gate",
"model.language_model.layers.30.mlp.gate",
"model.language_model.layers.31.mlp.gate",
"model.language_model.layers.32.mlp.gate",
"model.language_model.layers.33.mlp.gate",
"model.language_model.layers.34.mlp.gate",
"model.language_model.layers.35.mlp.gate",
"model.language_model.layers.36.mlp.gate",
"model.language_model.layers.37.mlp.gate",
"model.language_model.layers.38.mlp.gate",
"model.language_model.layers.39.mlp.gate",
"model.language_model.layers.40.mlp.gate",
"model.language_model.layers.41.mlp.gate",
"model.language_model.layers.42.mlp.gate",
"model.language_model.layers.43.mlp.gate",
"model.language_model.layers.44.mlp.gate",
"model.language_model.layers.45.mlp.gate",
"model.language_model.layers.46.mlp.gate",
"model.language_model.layers.47.mlp.gate",
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.12.1.dev0"
},
"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,
"router_aux_loss_coef": 0.001,
"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
}