Encoders / config.json
lightx2v's picture
Upload folder using huggingface_hub
90efac3 verified
raw
history blame
4.28 kB
{
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "float32",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "qwen2_5_vl",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"desc_act": false,
"format": "gptq",
"group_size": 128,
"lm_head": false,
"meta": {
"act_group_aware": true,
"damp_auto_increment": 0.01,
"damp_percent": 0.1,
"failsafe": {
"smooth": {
"group_size_threshold": 128,
"k": 2.75,
"type": "mad"
},
"strategy": "rtn",
"threshold": "0.5%"
},
"gptaq": false,
"gptaq_alpha": 0.25,
"gptaq_memory_device": "auto",
"hessian_chunk_bytes": null,
"hessian_chunk_size": null,
"hessian_use_bfloat16_staging": false,
"mock_quantization": false,
"mse": 0.0,
"offload_to_disk": true,
"offload_to_disk_path": "./gptqmodel_offload/hqdpgrum-rkaakpxx/",
"pack_impl": "cpu",
"quantizer": [
"gptqmodel:5.7.0-dev"
],
"static_groups": false,
"true_sequential": true,
"uri": "https://github.com/modelcloud/gptqmodel",
"vram_strategy": "exclusive"
},
"pack_dtype": "int32",
"quant_method": "gptq",
"sym": false
},
"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": {
"_name_or_path": "/data/nvme0/gushiqiao/models/code/model",
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "float32",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"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"
],
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "qwen2_5_vl_text",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"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,
"vision_token_id": 151654,
"vocab_size": 152064
},
"tie_word_embeddings": false,
"transformers_version": "4.57.3",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"depth": 32,
"dtype": "float32",
"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": 3420,
"model_type": "qwen2_5_vl",
"num_heads": 16,
"out_hidden_size": 3584,
"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
}