196 lines
4.5 KiB
JSON
196 lines
4.5 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Qwen2_5_VLForConditionalGeneration"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"image_token_id": 151655,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 27648,
|
||
|
|
"max_position_embeddings": 128000,
|
||
|
|
"max_window_layers": 64,
|
||
|
|
"model_type": "qwen2_5_vl",
|
||
|
|
"num_attention_heads": 40,
|
||
|
|
"num_hidden_layers": 64,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 151643,
|
||
|
|
"quantization_config": {
|
||
|
|
"bits": 4,
|
||
|
|
"checkpoint_format": "gptq",
|
||
|
|
"desc_act": true,
|
||
|
|
"group_size": 128,
|
||
|
|
"lm_head": false,
|
||
|
|
"meta": {
|
||
|
|
"act_group_aware": false,
|
||
|
|
"damp_auto_increment": 0.01,
|
||
|
|
"damp_percent": 0.05,
|
||
|
|
"mse": 0.0,
|
||
|
|
"quantizer": [
|
||
|
|
"gptqmodel:4.2.5"
|
||
|
|
],
|
||
|
|
"static_groups": false,
|
||
|
|
"true_sequential": true,
|
||
|
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
||
|
|
"v2": false,
|
||
|
|
"v2_alpha": 0.25
|
||
|
|
},
|
||
|
|
"pack_dtype": "int32",
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"sym": true
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": {
|
||
|
|
"mrope_section": [
|
||
|
|
16,
|
||
|
|
24,
|
||
|
|
24
|
||
|
|
],
|
||
|
|
"rope_type": "default",
|
||
|
|
"type": "default"
|
||
|
|
},
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"sliding_window": 32768,
|
||
|
|
"text_config": {
|
||
|
|
"architectures": [
|
||
|
|
"Qwen2_5_VLForConditionalGeneration"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"image_token_id": null,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 27648,
|
||
|
|
"layer_types": [
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention",
|
||
|
|
"full_attention"
|
||
|
|
],
|
||
|
|
"max_position_embeddings": 128000,
|
||
|
|
"max_window_layers": 64,
|
||
|
|
"model_type": "qwen2_5_vl_text",
|
||
|
|
"num_attention_heads": 40,
|
||
|
|
"num_hidden_layers": 64,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 151643,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": {
|
||
|
|
"mrope_section": [
|
||
|
|
16,
|
||
|
|
24,
|
||
|
|
24
|
||
|
|
],
|
||
|
|
"rope_type": "default",
|
||
|
|
"type": "default"
|
||
|
|
},
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"sliding_window": null,
|
||
|
|
"use_cache": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"video_token_id": null,
|
||
|
|
"vision_end_token_id": 151653,
|
||
|
|
"vision_start_token_id": 151652,
|
||
|
|
"vision_token_id": 151654,
|
||
|
|
"vocab_size": 152064
|
||
|
|
},
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"transformers_version": "4.56.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"video_token_id": 151656,
|
||
|
|
"vision_config": {
|
||
|
|
"depth": 32,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"fullatt_block_indexes": [
|
||
|
|
7,
|
||
|
|
15,
|
||
|
|
23,
|
||
|
|
31
|
||
|
|
],
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 1280,
|
||
|
|
"in_channels": 3,
|
||
|
|
"in_chans": 3,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 3456,
|
||
|
|
"model_type": "qwen2_5_vl",
|
||
|
|
"num_heads": 16,
|
||
|
|
"out_hidden_size": 5120,
|
||
|
|
"patch_size": 14,
|
||
|
|
"spatial_merge_size": 2,
|
||
|
|
"spatial_patch_size": 14,
|
||
|
|
"temporal_patch_size": 2,
|
||
|
|
"tokens_per_second": 2,
|
||
|
|
"window_size": 112
|
||
|
|
},
|
||
|
|
"vision_end_token_id": 151653,
|
||
|
|
"vision_start_token_id": 151652,
|
||
|
|
"vision_token_id": 151654,
|
||
|
|
"vocab_size": 152064
|
||
|
|
}
|