| { |
| "_class_name": "Krea2Transformer2DModel", |
| "_diffusers_version": "0.39.0.dev0", |
| "_name_or_path": "./tmp_model/transformer", |
| "attention_head_dim": 128, |
| "axes_dims_rope": [ |
| 32, |
| 48, |
| 48 |
| ], |
| "in_channels": 64, |
| "intermediate_size": 16384, |
| "norm_eps": 1e-05, |
| "num_attention_heads": 48, |
| "num_key_value_heads": 12, |
| "num_layers": 28, |
| "num_layerwise_text_blocks": 2, |
| "num_refiner_text_blocks": 2, |
| "num_text_layers": 12, |
| "quantization_config": { |
| "_load_in_4bit": true, |
| "_load_in_8bit": false, |
| "bnb_4bit_compute_dtype": "bfloat16", |
| "bnb_4bit_quant_storage": "uint8", |
| "bnb_4bit_quant_type": "nf4", |
| "bnb_4bit_use_double_quant": true, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": [ |
| "img_in", |
| "time_embed.linear_1", |
| "time_embed.linear_2", |
| "time_mod_proj", |
| "text_fusion.projector", |
| "txt_in.linear_1", |
| "txt_in.linear_2", |
| "final_layer.linear", |
| "text_fusion.layerwise_blocks.0.attn.to_q", |
| "text_fusion.layerwise_blocks.0.attn.to_k", |
| "text_fusion.layerwise_blocks.0.attn.to_v", |
| "text_fusion.layerwise_blocks.0.attn.to_gate", |
| "text_fusion.layerwise_blocks.0.attn.to_out.0", |
| "text_fusion.layerwise_blocks.0.ff.gate", |
| "text_fusion.layerwise_blocks.0.ff.up", |
| "text_fusion.layerwise_blocks.0.ff.down", |
| "text_fusion.layerwise_blocks.1.attn.to_q", |
| "text_fusion.layerwise_blocks.1.attn.to_k", |
| "text_fusion.layerwise_blocks.1.attn.to_v", |
| "text_fusion.layerwise_blocks.1.attn.to_gate", |
| "text_fusion.layerwise_blocks.1.attn.to_out.0", |
| "text_fusion.layerwise_blocks.1.ff.gate", |
| "text_fusion.layerwise_blocks.1.ff.up", |
| "text_fusion.layerwise_blocks.1.ff.down", |
| "text_fusion.refiner_blocks.0.attn.to_q", |
| "text_fusion.refiner_blocks.0.attn.to_k", |
| "text_fusion.refiner_blocks.0.attn.to_v", |
| "text_fusion.refiner_blocks.0.attn.to_gate", |
| "text_fusion.refiner_blocks.0.attn.to_out.0", |
| "text_fusion.refiner_blocks.0.ff.gate", |
| "text_fusion.refiner_blocks.0.ff.up", |
| "text_fusion.refiner_blocks.0.ff.down", |
| "text_fusion.refiner_blocks.1.attn.to_q", |
| "text_fusion.refiner_blocks.1.attn.to_k", |
| "text_fusion.refiner_blocks.1.attn.to_v", |
| "text_fusion.refiner_blocks.1.attn.to_gate", |
| "text_fusion.refiner_blocks.1.attn.to_out.0", |
| "text_fusion.refiner_blocks.1.ff.gate", |
| "text_fusion.refiner_blocks.1.ff.up", |
| "text_fusion.refiner_blocks.1.ff.down", |
| "transformer_blocks.0.attn.to_q", |
| "transformer_blocks.0.attn.to_k", |
| "transformer_blocks.0.attn.to_v", |
| "transformer_blocks.0.attn.to_gate", |
| "transformer_blocks.0.attn.to_out.0", |
| "transformer_blocks.0.ff.gate", |
| "transformer_blocks.0.ff.up", |
| "transformer_blocks.0.ff.down", |
| "transformer_blocks.27.attn.to_q", |
| "transformer_blocks.27.attn.to_k", |
| "transformer_blocks.27.attn.to_v", |
| "transformer_blocks.27.attn.to_gate", |
| "transformer_blocks.27.attn.to_out.0", |
| "transformer_blocks.27.ff.gate", |
| "transformer_blocks.27.ff.up", |
| "transformer_blocks.27.ff.down", |
| "norm", |
| "norm1", |
| "norm2", |
| "norm_q", |
| "norm_k" |
| ], |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": true, |
| "load_in_8bit": false, |
| "quant_method": "bitsandbytes" |
| }, |
| "rope_theta": 1000.0, |
| "text_hidden_dim": 2560, |
| "text_intermediate_size": 6912, |
| "text_num_attention_heads": 20, |
| "text_num_key_value_heads": 20, |
| "timestep_embed_dim": 256 |
| } |
|
|
