Upload configs.json with huggingface_hub

configs.json

@@ -1 +1 @@
-{"text_encoder": {"tokens_length": 128, "context_dim": 4096, "weights_path": "weights/flan_ul2_encoder/", "low_cpu_mem_usage": true, "load_in_8bit": false, "load_in_4bit": false}, "image_movq": {"configs": {"temporal": false, "temporal_attention_block": false, "temporal_kernel_size": [3, 3, 3], "temporal_conv_padding": [1, 1, 1], "double_z": false, "z_channels": 4, "resolution": 256, "in_channels": 3, "out_ch": 3, "ch": 256, "ch_mult": [1, 2, 2, 4], "num_res_blocks": 2, "attn_resolutions": [32], "dropout": 0.0}}, "video_movq": {"configs": {"temporal": true, "temporal_attention_block": true, "temporal_kernel_size": [3, 3, 3], "temporal_conv_padding": [1, 1, 1], "double_z": false, "z_channels": 4, "resolution": 256, "in_channels": 3, "out_ch": 3, "ch": 256, "ch_mult": [1, 2, 2, 4], "num_res_blocks": 2, "attn_resolutions": [32], "dropout": 0.0}}, "t2v": {"configs": {"model_channels": 384, "num_channels": 9, "out_channels": 4, "init_channels": 192, "time_embed_dim": 1536, "context_dim": 4096, "groups": 32, "head_dim": 64, "expansion_ratio": 4, "compression_ratio": 2, "dim_mult": [1, 2, 4, 8], "num_blocks": [3, 3, 3, 3], "add_cross_attention": [false, true, true, true], "add_self_attention": [false, true, true, true], "noise_augmentation": true, "motion_score": true}}, "interpolation": {"configs": {"model_channels": 384, "num_channels": 20, "out_channels": 12, "init_channels": 192, "time_embed_dim": 1536, "context_dim": 4096, "groups": 32, "head_dim": 64, "expansion_ratio": 4, "compression_ratio": 2, "dim_mult": [1, 2, 4, 8], "num_blocks": [3, 3, 3, 3], "add_cross_attention": [false, true, true, true], "add_self_attention": [false, true, true, true]}}}
+{"text_encoder": {"tokens_length": 128, "context_dim": 4096, "weights_path": "google/flan-ul2", "low_cpu_mem_usage": true, "load_in_8bit": false, "load_in_4bit": false}, "image_movq": {"configs": {"temporal": false, "temporal_attention_block": false, "temporal_kernel_size": [3, 3, 3], "temporal_conv_padding": [1, 1, 1], "double_z": false, "z_channels": 4, "resolution": 256, "in_channels": 3, "out_ch": 3, "ch": 256, "ch_mult": [1, 2, 2, 4], "num_res_blocks": 2, "attn_resolutions": [32], "dropout": 0.0}}, "video_movq": {"configs": {"temporal": true, "temporal_attention_block": true, "temporal_kernel_size": [3, 3, 3], "temporal_conv_padding": [1, 1, 1], "double_z": false, "z_channels": 4, "resolution": 256, "in_channels": 3, "out_ch": 3, "ch": 256, "ch_mult": [1, 2, 2, 4], "num_res_blocks": 2, "attn_resolutions": [32], "dropout": 0.0}}, "t2v": {"configs": {"model_channels": 384, "num_channels": 9, "out_channels": 4, "init_channels": 192, "time_embed_dim": 1536, "context_dim": 4096, "groups": 32, "head_dim": 64, "expansion_ratio": 4, "compression_ratio": 2, "dim_mult": [1, 2, 4, 8], "num_blocks": [3, 3, 3, 3], "add_cross_attention": [false, true, true, true], "add_self_attention": [false, true, true, true], "noise_augmentation": true, "motion_score": true}}, "interpolation": {"configs": {"model_channels": 384, "num_channels": 20, "out_channels": 12, "init_channels": 192, "time_embed_dim": 1536, "context_dim": 4096, "groups": 32, "head_dim": 64, "expansion_ratio": 4, "compression_ratio": 2, "dim_mult": [1, 2, 4, 8], "num_blocks": [3, 3, 3, 3], "add_cross_attention": [false, true, true, true], "add_self_attention": [false, true, true, true]}}}