92 lines
2.4 KiB
JSON
92 lines
2.4 KiB
JSON
{
|
|
"architectures": [
|
|
"InternVLChatModel"
|
|
],
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
|
|
"AutoModel": "modeling_internvl_chat.InternVLChatModel",
|
|
"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
|
|
},
|
|
"downsample_ratio": 0.5,
|
|
"dynamic_image_size": true,
|
|
"eos_token_id": 151645,
|
|
"force_image_size": 448,
|
|
"llm_config": {
|
|
"_name_or_path": "/root/codespace/checkpoints/Qwen3-14B",
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"debug": false,
|
|
"eos_token_id": 151645,
|
|
"ep_size": 1,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 17408,
|
|
"max_position_embeddings": 40960,
|
|
"max_window_layers": 40,
|
|
"micro_forward": false,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"skip_checkpoint": false,
|
|
"sliding_window": null,
|
|
"torch_dtype": "bfloat16",
|
|
"use_cache": false,
|
|
"use_deepep": false,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
},
|
|
"max_dynamic_patch": 12,
|
|
"min_dynamic_patch": 1,
|
|
"model_type": "internvl_chat",
|
|
"pad2square": false,
|
|
"pad_token_id": 151643,
|
|
"ps_version": "v2",
|
|
"select_layer": -1,
|
|
"template": "internvl2_5",
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": null,
|
|
"use_backbone_lora": 0,
|
|
"use_llm_lora": 0,
|
|
"use_thumbnail": true,
|
|
"vision_config": {
|
|
"architectures": [
|
|
"InternVisionModel"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
|
|
"AutoModel": "modeling_intern_vit.InternVisionModel"
|
|
},
|
|
"drop_path_rate": 0.0,
|
|
"dropout": 0.0,
|
|
"hidden_act": "gelu",
|
|
"hidden_size": 1024,
|
|
"image_size": 448,
|
|
"initializer_factor": 1.0,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 4096,
|
|
"layer_norm_eps": 1e-06,
|
|
"model_type": "intern_vit_6b",
|
|
"norm_type": "layer_norm",
|
|
"num_attention_heads": 16,
|
|
"num_channels": 3,
|
|
"num_hidden_layers": 24,
|
|
"patch_size": 14,
|
|
"qk_normalization": false,
|
|
"qkv_bias": true,
|
|
"torch_dtype": "bfloat16",
|
|
"use_fa3": false,
|
|
"use_flash_attn": true
|
|
}
|
|
} |