初始化项目,由ModelHub XC社区提供模型
Model: unsloth/Qwen3-VL-4B-Instruct-FP8 Source: Original Platform
This commit is contained in:
325
config.json
Normal file
325
config.json
Normal file
@@ -0,0 +1,325 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3VLForConditionalGeneration"
|
||||
],
|
||||
"image_token_id": 151655,
|
||||
"model_type": "qwen3_vl",
|
||||
"pad_token_id": 151654,
|
||||
"quantization_config": {
|
||||
"activation_scheme": "dynamic",
|
||||
"fmt": "e4m3",
|
||||
"ignored_layers": [
|
||||
"lm_head",
|
||||
"model.visual.merger.linear_fc1",
|
||||
"model.visual.merger.linear_fc2",
|
||||
"model.visual.merger.norm",
|
||||
"model.visual.patch_embed.proj",
|
||||
"model.visual.pos_embed",
|
||||
"visual.merger.linear_fc1",
|
||||
"visual.merger.linear_fc2",
|
||||
"visual.merger.norm",
|
||||
"visual.patch_embed.proj",
|
||||
"visual.pos_embed",
|
||||
"model.visual.blocks.0.attn.proj",
|
||||
"model.visual.blocks.0.attn.qkv",
|
||||
"model.visual.blocks.0.mlp.linear_fc1",
|
||||
"model.visual.blocks.0.mlp.linear_fc2",
|
||||
"visual.blocks.0.attn.proj",
|
||||
"visual.blocks.0.attn.qkv_proj",
|
||||
"visual.blocks.0.mlp.linear_fc1",
|
||||
"visual.blocks.0.mlp.linear_fc2",
|
||||
"model.visual.blocks.1.attn.proj",
|
||||
"model.visual.blocks.1.attn.qkv",
|
||||
"model.visual.blocks.1.mlp.linear_fc1",
|
||||
"model.visual.blocks.1.mlp.linear_fc2",
|
||||
"visual.blocks.1.attn.proj",
|
||||
"visual.blocks.1.attn.qkv_proj",
|
||||
"visual.blocks.1.mlp.linear_fc1",
|
||||
"visual.blocks.1.mlp.linear_fc2",
|
||||
"model.visual.blocks.2.attn.proj",
|
||||
"model.visual.blocks.2.attn.qkv",
|
||||
"model.visual.blocks.2.mlp.linear_fc1",
|
||||
"model.visual.blocks.2.mlp.linear_fc2",
|
||||
"visual.blocks.2.attn.proj",
|
||||
"visual.blocks.2.attn.qkv_proj",
|
||||
"visual.blocks.2.mlp.linear_fc1",
|
||||
"visual.blocks.2.mlp.linear_fc2",
|
||||
"model.visual.blocks.3.attn.proj",
|
||||
"model.visual.blocks.3.attn.qkv",
|
||||
"model.visual.blocks.3.mlp.linear_fc1",
|
||||
"model.visual.blocks.3.mlp.linear_fc2",
|
||||
"visual.blocks.3.attn.proj",
|
||||
"visual.blocks.3.attn.qkv_proj",
|
||||
"visual.blocks.3.mlp.linear_fc1",
|
||||
"visual.blocks.3.mlp.linear_fc2",
|
||||
"model.visual.blocks.4.attn.proj",
|
||||
"model.visual.blocks.4.attn.qkv",
|
||||
"model.visual.blocks.4.mlp.linear_fc1",
|
||||
"model.visual.blocks.4.mlp.linear_fc2",
|
||||
"visual.blocks.4.attn.proj",
|
||||
"visual.blocks.4.attn.qkv_proj",
|
||||
"visual.blocks.4.mlp.linear_fc1",
|
||||
"visual.blocks.4.mlp.linear_fc2",
|
||||
"model.visual.blocks.5.attn.proj",
|
||||
"model.visual.blocks.5.attn.qkv",
|
||||
"model.visual.blocks.5.mlp.linear_fc1",
|
||||
"model.visual.blocks.5.mlp.linear_fc2",
|
||||
"visual.blocks.5.attn.proj",
|
||||
"visual.blocks.5.attn.qkv_proj",
|
||||
"visual.blocks.5.mlp.linear_fc1",
|
||||
"visual.blocks.5.mlp.linear_fc2",
|
||||
"model.visual.blocks.6.attn.proj",
|
||||
"model.visual.blocks.6.attn.qkv",
|
||||
"model.visual.blocks.6.mlp.linear_fc1",
|
||||
"model.visual.blocks.6.mlp.linear_fc2",
|
||||
"visual.blocks.6.attn.proj",
|
||||
"visual.blocks.6.attn.qkv_proj",
|
||||
"visual.blocks.6.mlp.linear_fc1",
|
||||
"visual.blocks.6.mlp.linear_fc2",
|
||||
"model.visual.blocks.7.attn.proj",
|
||||
"model.visual.blocks.7.attn.qkv",
|
||||
"model.visual.blocks.7.mlp.linear_fc1",
|
||||
"model.visual.blocks.7.mlp.linear_fc2",
|
||||
"visual.blocks.7.attn.proj",
|
||||
"visual.blocks.7.attn.qkv_proj",
|
||||
"visual.blocks.7.mlp.linear_fc1",
|
||||
"visual.blocks.7.mlp.linear_fc2",
|
||||
"model.visual.blocks.8.attn.proj",
|
||||
"model.visual.blocks.8.attn.qkv",
|
||||
"model.visual.blocks.8.mlp.linear_fc1",
|
||||
"model.visual.blocks.8.mlp.linear_fc2",
|
||||
"visual.blocks.8.attn.proj",
|
||||
"visual.blocks.8.attn.qkv_proj",
|
||||
"visual.blocks.8.mlp.linear_fc1",
|
||||
"visual.blocks.8.mlp.linear_fc2",
|
||||
"model.visual.blocks.9.attn.proj",
|
||||
"model.visual.blocks.9.attn.qkv",
|
||||
"model.visual.blocks.9.mlp.linear_fc1",
|
||||
"model.visual.blocks.9.mlp.linear_fc2",
|
||||
"visual.blocks.9.attn.proj",
|
||||
"visual.blocks.9.attn.qkv_proj",
|
||||
"visual.blocks.9.mlp.linear_fc1",
|
||||
"visual.blocks.9.mlp.linear_fc2",
|
||||
"model.visual.blocks.10.attn.proj",
|
||||
"model.visual.blocks.10.attn.qkv",
|
||||
"model.visual.blocks.10.mlp.linear_fc1",
|
||||
"model.visual.blocks.10.mlp.linear_fc2",
|
||||
"visual.blocks.10.attn.proj",
|
||||
"visual.blocks.10.attn.qkv_proj",
|
||||
"visual.blocks.10.mlp.linear_fc1",
|
||||
"visual.blocks.10.mlp.linear_fc2",
|
||||
"model.visual.blocks.11.attn.proj",
|
||||
"model.visual.blocks.11.attn.qkv",
|
||||
"model.visual.blocks.11.mlp.linear_fc1",
|
||||
"model.visual.blocks.11.mlp.linear_fc2",
|
||||
"visual.blocks.11.attn.proj",
|
||||
"visual.blocks.11.attn.qkv_proj",
|
||||
"visual.blocks.11.mlp.linear_fc1",
|
||||
"visual.blocks.11.mlp.linear_fc2",
|
||||
"model.visual.blocks.12.attn.proj",
|
||||
"model.visual.blocks.12.attn.qkv",
|
||||
"model.visual.blocks.12.mlp.linear_fc1",
|
||||
"model.visual.blocks.12.mlp.linear_fc2",
|
||||
"visual.blocks.12.attn.proj",
|
||||
"visual.blocks.12.attn.qkv_proj",
|
||||
"visual.blocks.12.mlp.linear_fc1",
|
||||
"visual.blocks.12.mlp.linear_fc2",
|
||||
"model.visual.blocks.13.attn.proj",
|
||||
"model.visual.blocks.13.attn.qkv",
|
||||
"model.visual.blocks.13.mlp.linear_fc1",
|
||||
"model.visual.blocks.13.mlp.linear_fc2",
|
||||
"visual.blocks.13.attn.proj",
|
||||
"visual.blocks.13.attn.qkv_proj",
|
||||
"visual.blocks.13.mlp.linear_fc1",
|
||||
"visual.blocks.13.mlp.linear_fc2",
|
||||
"model.visual.blocks.14.attn.proj",
|
||||
"model.visual.blocks.14.attn.qkv",
|
||||
"model.visual.blocks.14.mlp.linear_fc1",
|
||||
"model.visual.blocks.14.mlp.linear_fc2",
|
||||
"visual.blocks.14.attn.proj",
|
||||
"visual.blocks.14.attn.qkv_proj",
|
||||
"visual.blocks.14.mlp.linear_fc1",
|
||||
"visual.blocks.14.mlp.linear_fc2",
|
||||
"model.visual.blocks.15.attn.proj",
|
||||
"model.visual.blocks.15.attn.qkv",
|
||||
"model.visual.blocks.15.mlp.linear_fc1",
|
||||
"model.visual.blocks.15.mlp.linear_fc2",
|
||||
"visual.blocks.15.attn.proj",
|
||||
"visual.blocks.15.attn.qkv_proj",
|
||||
"visual.blocks.15.mlp.linear_fc1",
|
||||
"visual.blocks.15.mlp.linear_fc2",
|
||||
"model.visual.blocks.16.attn.proj",
|
||||
"model.visual.blocks.16.attn.qkv",
|
||||
"model.visual.blocks.16.mlp.linear_fc1",
|
||||
"model.visual.blocks.16.mlp.linear_fc2",
|
||||
"visual.blocks.16.attn.proj",
|
||||
"visual.blocks.16.attn.qkv_proj",
|
||||
"visual.blocks.16.mlp.linear_fc1",
|
||||
"visual.blocks.16.mlp.linear_fc2",
|
||||
"model.visual.blocks.17.attn.proj",
|
||||
"model.visual.blocks.17.attn.qkv",
|
||||
"model.visual.blocks.17.mlp.linear_fc1",
|
||||
"model.visual.blocks.17.mlp.linear_fc2",
|
||||
"visual.blocks.17.attn.proj",
|
||||
"visual.blocks.17.attn.qkv_proj",
|
||||
"visual.blocks.17.mlp.linear_fc1",
|
||||
"visual.blocks.17.mlp.linear_fc2",
|
||||
"model.visual.blocks.18.attn.proj",
|
||||
"model.visual.blocks.18.attn.qkv",
|
||||
"model.visual.blocks.18.mlp.linear_fc1",
|
||||
"model.visual.blocks.18.mlp.linear_fc2",
|
||||
"visual.blocks.18.attn.proj",
|
||||
"visual.blocks.18.attn.qkv_proj",
|
||||
"visual.blocks.18.mlp.linear_fc1",
|
||||
"visual.blocks.18.mlp.linear_fc2",
|
||||
"model.visual.blocks.19.attn.proj",
|
||||
"model.visual.blocks.19.attn.qkv",
|
||||
"model.visual.blocks.19.mlp.linear_fc1",
|
||||
"model.visual.blocks.19.mlp.linear_fc2",
|
||||
"visual.blocks.19.attn.proj",
|
||||
"visual.blocks.19.attn.qkv_proj",
|
||||
"visual.blocks.19.mlp.linear_fc1",
|
||||
"visual.blocks.19.mlp.linear_fc2",
|
||||
"model.visual.blocks.20.attn.proj",
|
||||
"model.visual.blocks.20.attn.qkv",
|
||||
"model.visual.blocks.20.mlp.linear_fc1",
|
||||
"model.visual.blocks.20.mlp.linear_fc2",
|
||||
"visual.blocks.20.attn.proj",
|
||||
"visual.blocks.20.attn.qkv_proj",
|
||||
"visual.blocks.20.mlp.linear_fc1",
|
||||
"visual.blocks.20.mlp.linear_fc2",
|
||||
"model.visual.blocks.21.attn.proj",
|
||||
"model.visual.blocks.21.attn.qkv",
|
||||
"model.visual.blocks.21.mlp.linear_fc1",
|
||||
"model.visual.blocks.21.mlp.linear_fc2",
|
||||
"visual.blocks.21.attn.proj",
|
||||
"visual.blocks.21.attn.qkv_proj",
|
||||
"visual.blocks.21.mlp.linear_fc1",
|
||||
"visual.blocks.21.mlp.linear_fc2",
|
||||
"model.visual.blocks.22.attn.proj",
|
||||
"model.visual.blocks.22.attn.qkv",
|
||||
"model.visual.blocks.22.mlp.linear_fc1",
|
||||
"model.visual.blocks.22.mlp.linear_fc2",
|
||||
"visual.blocks.22.attn.proj",
|
||||
"visual.blocks.22.attn.qkv_proj",
|
||||
"visual.blocks.22.mlp.linear_fc1",
|
||||
"visual.blocks.22.mlp.linear_fc2",
|
||||
"model.visual.blocks.23.attn.proj",
|
||||
"model.visual.blocks.23.attn.qkv",
|
||||
"model.visual.blocks.23.mlp.linear_fc1",
|
||||
"model.visual.blocks.23.mlp.linear_fc2",
|
||||
"visual.blocks.23.attn.proj",
|
||||
"visual.blocks.23.attn.qkv_proj",
|
||||
"visual.blocks.23.mlp.linear_fc1",
|
||||
"visual.blocks.23.mlp.linear_fc2",
|
||||
"model.visual.blocks.24.attn.proj",
|
||||
"model.visual.blocks.24.attn.qkv",
|
||||
"model.visual.blocks.24.mlp.linear_fc1",
|
||||
"model.visual.blocks.24.mlp.linear_fc2",
|
||||
"visual.blocks.24.attn.proj",
|
||||
"visual.blocks.24.attn.qkv_proj",
|
||||
"visual.blocks.24.mlp.linear_fc1",
|
||||
"visual.blocks.24.mlp.linear_fc2",
|
||||
"model.visual.blocks.25.attn.proj",
|
||||
"model.visual.blocks.25.attn.qkv",
|
||||
"model.visual.blocks.25.mlp.linear_fc1",
|
||||
"model.visual.blocks.25.mlp.linear_fc2",
|
||||
"visual.blocks.25.attn.proj",
|
||||
"visual.blocks.25.attn.qkv_proj",
|
||||
"visual.blocks.25.mlp.linear_fc1",
|
||||
"visual.blocks.25.mlp.linear_fc2",
|
||||
"model.visual.blocks.26.attn.proj",
|
||||
"model.visual.blocks.26.attn.qkv",
|
||||
"model.visual.blocks.26.mlp.linear_fc1",
|
||||
"model.visual.blocks.26.mlp.linear_fc2",
|
||||
"visual.blocks.26.attn.proj",
|
||||
"visual.blocks.26.attn.qkv_proj",
|
||||
"visual.blocks.26.mlp.linear_fc1",
|
||||
"visual.blocks.26.mlp.linear_fc2",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc1",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc2",
|
||||
"model.visual.deepstack_merger_list.0.norm",
|
||||
"visual.deepstack_merger_list.0.linear_fc1",
|
||||
"visual.deepstack_merger_list.0.linear_fc2",
|
||||
"visual.deepstack_merger_list.0.norm",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc1",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc2",
|
||||
"model.visual.deepstack_merger_list.1.norm",
|
||||
"visual.deepstack_merger_list.1.linear_fc1",
|
||||
"visual.deepstack_merger_list.1.linear_fc2",
|
||||
"visual.deepstack_merger_list.1.norm",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc1",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc2",
|
||||
"model.visual.deepstack_merger_list.2.norm",
|
||||
"visual.deepstack_merger_list.2.linear_fc1",
|
||||
"visual.deepstack_merger_list.2.linear_fc2",
|
||||
"visual.deepstack_merger_list.2.norm"
|
||||
],
|
||||
"modules_to_not_convert": [
|
||||
"lm_head",
|
||||
"model.visual"
|
||||
],
|
||||
"quant_method": "fp8",
|
||||
"weight_block_size": [
|
||||
128,
|
||||
128
|
||||
]
|
||||
},
|
||||
"text_config": {
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"torch_dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"max_position_embeddings": 262144,
|
||||
"model_type": "qwen3_vl_text",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_interleaved": true,
|
||||
"mrope_section": [
|
||||
24,
|
||||
20,
|
||||
20
|
||||
],
|
||||
"rope_type": "default"
|
||||
},
|
||||
"rope_theta": 5000000,
|
||||
"tie_word_embeddings": true,
|
||||
"use_cache": true,
|
||||
"vocab_size": 151936
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"unsloth_fixed": true,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"deepstack_visual_indexes": [
|
||||
5,
|
||||
11,
|
||||
17
|
||||
],
|
||||
"depth": 24,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1024,
|
||||
"in_channels": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"model_type": "qwen3_vl",
|
||||
"num_heads": 16,
|
||||
"num_position_embeddings": 2304,
|
||||
"out_hidden_size": 2560,
|
||||
"patch_size": 16,
|
||||
"spatial_merge_size": 2,
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652
|
||||
}
|
||||
Reference in New Issue
Block a user