Jingya's picture
Jingya HF staff
Synchronizing local compiler cache.
610e598 verified
raw
history blame
3.55 kB
{
"_class_name": "UNet2DConditionModel",
"_commit_hash": null,
"_diffusers_version": "0.26.3",
"_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/unet",
"_use_default_values": [
"timestep_post_act",
"attention_type",
"encoder_hid_dim",
"class_embeddings_concat",
"dual_cross_attention",
"class_embed_type",
"addition_time_embed_dim",
"use_linear_projection",
"time_embedding_act_fn",
"upcast_attention",
"only_cross_attention",
"reverse_transformer_layers_per_block",
"mid_block_type",
"time_embedding_type",
"num_attention_heads",
"transformer_layers_per_block",
"resnet_skip_time_act",
"conv_in_kernel",
"cross_attention_norm",
"resnet_time_scale_shift",
"conv_out_kernel",
"projection_class_embeddings_input_dim",
"addition_embed_type_num_heads",
"dropout",
"addition_embed_type",
"time_embedding_dim",
"resnet_out_scale_factor",
"time_cond_proj_dim",
"encoder_hid_dim_type",
"mid_block_only_cross_attention",
"num_class_embeds"
],
"act_fn": "silu",
"addition_embed_type": null,
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": null,
"attention_head_dim": 8,
"attention_type": "default",
"block_out_channels": [
320,
640,
1280,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 768,
"cross_attention_norm": null,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"dropout": 0.0,
"dual_cross_attention": false,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"neuron": {
"auto_cast": "matmul",
"auto_cast_type": "bf16",
"compiler_type": "neuronx-cc",
"compiler_version": "2.12.68.0+4480452af",
"dynamic_batch_size": false,
"inline_weights_to_neff": false,
"input_names": [
"sample",
"timestep",
"encoder_hidden_states"
],
"model_type": "unet",
"optlevel": "2",
"output_attentions": false,
"output_hidden_states": false,
"output_names": [
"sample"
],
"static_batch_size": 1,
"static_height": 64,
"static_num_channels": 4,
"static_sequence_length": 77,
"static_width": 64
},
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": null,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 64,
"task": "semantic-segmentation",
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": 1,
"transformers_version": null,
"up_block_types": [
"UpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": false
}