Synchronizing local compiler cache.

.gitattributes

@@ -1278,3 +1278,26 @@ neuronxcc-2.15.141.0+d3cfc8ca/MODULE_ff056ff915e121ff695e+39f12043/model.neff fi
 neuronxcc-2.15.141.0+d3cfc8ca/MODULE_70ee399e6fa6b6235418+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.141.0+d3cfc8ca/MODULE_b0cf61abda16eb6dab0b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.141.0+d3cfc8ca/MODULE_8c93cc9f80cd5bfc3ec7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_12874312700001148778+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_15051065331470346867+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_15473681725457350439+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_2091506504151733078+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_2466414372820998287+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_3419338939774422803+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_410438226797912832+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_4e375a5e1d159c319c4a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_5969785301766543355+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_6503304240059240709+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_6924851687386500240+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_8537207931352873960+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_8a7c00a8b0553e557d61+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_9211227249597385740+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_a8879c3265be017037a3+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_bb8d7ab74e3895d55e5a/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_bb8d7ab74e3895d55e5a/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_bb8d7ab74e3895d55e5a/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_caf1acf2b79f887a9c1f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_e0424cc49086a4e14ecf/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_e0424cc49086a4e14ecf/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_e0424cc49086a4e14ecf/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.128.0+56dc5a86/MODULE_eebabf12988462d4bdc0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/b4a7573c4f811bffe269.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/c38f7bf56dcb224f566b.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/distilbert/philschmid/tiny-distilbert-classification/f38fc51a7949ff88adae.json

@@ -0,0 +1 @@
+{"activation": "gelu", "architectures": ["DistilBertForSequenceClassification"], "attention_dropout": 0.1, "dim": 2, "dropout": 0.1, "finetuning_task": "sst-2", "hidden_dim": 2, "id2label": {"0": "NEGATIVE", "1": "POSITIVE"}, "initializer_range": 0.02, "label2id": {"NEGATIVE": 0, "POSITIVE": 1}, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 2, "n_layers": 2, "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 128}, "output_past": true, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "task": "text-classification", "tie_weights_": true, "vocab_size": 30522}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/f6a893091677c8cb5c41.json

@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 128, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/meta-llama/Llama-3.1-8B-Instruct/b4a7573c4f811bffe269.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/meta-llama/Llama-3.1-8B-Instruct/c38f7bf56dcb224f566b.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/asntr/tiny-stable-diffusion-pix2pix-torch/ea7b1231493b4770ef5c.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "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": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": 8, "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 8, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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, "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, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-latent-consistency/a0266aea820b4bdc6179.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 64, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 8, "num_hidden_layers": 3, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "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": [4, 8], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": 1, "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 2, "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, "task": "semantic-segmentation", "time_cond_proj_dim": 32, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/32eb77afae7beb1b6a46.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "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, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/69ca6952a5ae96368225.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "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, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/929dae9e65a3e8ca843a.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": true, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": true, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "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, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/daff12b814ed88f2ab94.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 4, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "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, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/e0424cc49086a4e14ecf.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 4, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "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, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/3b9c2d8b0685c83df7a8.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "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": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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, "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, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/9ebf77ef54b550a7aeea.json

@@ -0,0 +1 @@
+{"controlnet_0": {"_class_name": "ControlNetModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "block_out_channels": [32, 64], "class_embed_type": null, "conditioning_channels": 3, "conditioning_embedding_out_channels": [16, 32], "controlnet_conditioning_channel_order": "rgb", "cross_attention_dim": 32, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "global_pool_conditions": false, "in_channels": 4, "layers_per_block": 2, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_encoder_hidden_size": 32, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "projection_class_embeddings_input_dim": null, "resnet_time_scale_shift": "default", "task": "semantic-segmentation", "transformer_layers_per_block": 1, "upcast_attention": false, "use_linear_projection": false}, "model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "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": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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, "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, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/bb8d7ab74e3895d55e5a.json

@@ -0,0 +1 @@
+{"controlnet_0": {"_class_name": "ControlNetModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "block_out_channels": [32, 64], "class_embed_type": null, "conditioning_channels": 3, "conditioning_embedding_out_channels": [16, 32], "controlnet_conditioning_channel_order": "rgb", "cross_attention_dim": 32, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "global_pool_conditions": false, "in_channels": 4, "layers_per_block": 2, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_encoder_hidden_size": 32, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "projection_class_embeddings_input_dim": null, "resnet_time_scale_shift": "default", "task": "semantic-segmentation", "transformer_layers_per_block": 1, "upcast_attention": false, "use_linear_projection": false}, "controlnet_1": {"_class_name": "ControlNetModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "block_out_channels": [32, 64], "class_embed_type": null, "conditioning_channels": 3, "conditioning_embedding_out_channels": [16, 32], "controlnet_conditioning_channel_order": "rgb", "cross_attention_dim": 32, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "global_pool_conditions": false, "in_channels": 4, "layers_per_block": 2, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_encoder_hidden_size": 32, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "projection_class_embeddings_input_dim": null, "resnet_time_scale_shift": "default", "task": "semantic-segmentation", "transformer_layers_per_block": 1, "upcast_attention": false, "use_linear_projection": false}, "model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "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": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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, "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, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/bf44efc41469e0a7cc8c.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "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": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 4, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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, "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, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/de03d21e9973871dbb35.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "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": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "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": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "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, "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, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/6b3192766c61d426df54.json

@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 24, "sequence_length": 512, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}

neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/12c129f098b7cebc86c4.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "57a73110702e7b05ba3f39fef36297454c680725", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.15.128.0+56dc5a86/MODULE_1017888704236904008+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.128.0+56dc5a86/MODULE_1017888704236904008+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715629b6c6cbfb933557a7021fca2984bf5b1952c2c8e153314496dae9e6e871
+size 1346

neuronxcc-2.15.128.0+56dc5a86/MODULE_11714589375820305435+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.128.0+56dc5a86/MODULE_11714589375820305435+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec48b1cf0960333c4135337a092aef44c278eebbf3c8855383bd907c4117e373
+size 274304

neuronxcc-2.15.128.0+56dc5a86/MODULE_11939774322871528000+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.128.0+56dc5a86/MODULE_11939774322871528000+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69bb7805b97852de9492cdf1c433ea53dbb98e2fa61ccb6306daace54109d4b8
+size 6763

neuronxcc-2.15.128.0+56dc5a86/MODULE_1235400346242488257+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.128.0+56dc5a86/MODULE_1235400346242488257+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1a5f527c8bff5cac1e629bf9c27f0b5e0b0483718a252b4798f2ca48e94c3a
+size 1102

neuronxcc-2.15.128.0+56dc5a86/MODULE_12874312700001148778+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.128.0+56dc5a86/MODULE_12874312700001148778+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e5b85e2bf8cb27bdeb09aa220ff907c353c884c0d98222697943ce9aff0ae7
+size 442045

neuronxcc-2.15.128.0+56dc5a86/MODULE_12874312700001148778+d7517139/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6836ba761f1352c916d34b7ebbe5a5aca66c15ad0a08cb0cd4fda7534ec32f51
+size 13825024

neuronxcc-2.15.128.0+56dc5a86/MODULE_14508070509266123383+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.128.0+56dc5a86/MODULE_14508070509266123383+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cba5b5fde262cd470df29943359e9d1c085a7314d283de65529970a11358fd
+size 1867

neuronxcc-2.15.128.0+56dc5a86/MODULE_15051065331470346867+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.128.0+56dc5a86/MODULE_15051065331470346867+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a47c22b9c96c7f062e126bd9a2faec87f41ad7ac71f7285cfd4c716c9d3547
+size 411920

neuronxcc-2.15.128.0+56dc5a86/MODULE_15051065331470346867+d7517139/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1cac8f75624b69f4f5cc0ec9131f2c0d1d41511acf1e8e586b10b85645f173
+size 4219904

neuronxcc-2.15.128.0+56dc5a86/MODULE_15473681725457350439+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]