Synchronizing local compiler cache.

.gitattributes

@@ -2075,3 +2075,63 @@ neuronxcc-2.17.118.0+94814779/MODULE_f8d465a2f79c549360ef/text_encoder/model.neu
 neuronxcc-2.17.118.0+94814779/MODULE_f8d465a2f79c549360ef/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.118.0+94814779/MODULE_f8d465a2f79c549360ef/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.118.0+94814779/MODULE_f8d465a2f79c549360ef/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_068ef074748718999f13+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_13458a001a4a6d6c5895+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_1649fc77b87fff02e370+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_18ea862943d46e9502fe/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_1af7783366403652ad51+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_2053b1e0fa543cbd84dd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_22cf23062ec53b3fd95d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_23c20ba5fd4672262b4f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_2a10c038669fa2d343e1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_2a213e0741594f10219d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_2b761d9812991a0ed26f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_2ef52130792b59d66c66+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_2f59caeb45329072d7b0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_2fa982b13af96f760a14+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_3043604d5429432a4ae1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_3061bfbd0d476b938719+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_30a395d0dd4232fed110+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_3d8b2e723048c421570a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_3da832fdaa3d62981800+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_40b73cdf6e14999378ef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_4dea33d55b39527f7fc4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_54947fa9c379486e4f5b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_56bfdcf572244e4771f8+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_59ddd6977b34718ba8b1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_6886ba3bbca51509cd6c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_767d2f94879ca86f93cb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_7e2686740d19496c3c6e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_843d9f5ba8d442721b5e/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_878607c2d60970a9fc41+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_899a6dab3f2005ac207a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_8a3cac67f02909d50819+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_8b728c26e7384d3aa1fa+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_905ba6adc472b9f33cc6+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_913f4e1e2b4632438fe9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_94fd7c020f22384f6d27+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_95dae70c69a000bb4eb6+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_9dc5393f49942ebdc1af+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_9f4e39af4e0b35889393+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_9f5a907ba7db9a6a1e51+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_a6569d9c9d00e3812134+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_b9e80b41756cf2d7ed45+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_bdda47cac156ea8ffbfc+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_bf816c8623b1fd6b9185+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_cea91d96c873419351af+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_ceb1532721b05ed70905+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_da84b070ab21ed1df54f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_e10fffbed4e6a5dd8ea5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_e9bcfc17d832317203bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_f4c26fe7dbc0d9182bc8+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_f7a493b3a1ae24ab8ebb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_fa8e5e93b134884838d5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_fadc62f786e9e6e1bf75+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/distilbert/distilbert-base-uncased-finetuned-sst-2-english/843d9f5ba8d442721b5e.json

@@ -0,0 +1 @@
+{"_attn_implementation_autoset": true, "activation": "gelu", "architectures": ["DistilBertForSequenceClassification"], "attention_dropout": 0.1, "dim": 768, "dropout": 0.1, "finetuning_task": "sst-2", "hidden_dim": 3072, "id2label": {"0": "NEGATIVE", "1": "POSITIVE"}, "initializer_range": 0.02, "label2id": {"NEGATIVE": 0, "POSITIVE": 1}, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 12, "n_layers": 6, "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 128, "tensor_parallel_size": 1}, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/distilbert/hf-internal-testing/tiny-random-DistilBertModel/18ea862943d46e9502fe.json

@@ -0,0 +1 @@
+{"_attn_implementation_autoset": true, "activation": "gelu", "architectures": ["DistilBertModel"], "attention_dropout": 0.1, "dim": 32, "dropout": 0.1, "hidden_act": "gelu", "hidden_dim": 37, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 4, "n_layers": 5, "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 128, "tensor_parallel_size": 1}, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "task": "feature-extraction", "vocab_size": 1124}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/d8d5221e2ff47fe2e810.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": "bf16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-2b-instruct/051e0fbc95b7ee8fe6d4.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.015625, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "logits_scaling": 8.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", "checkpoint_revision": "374ef54e020a3ce208c65e96d6213922a87d8952", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-2b-instruct/23444ebd5ec165c6b78e.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.015625, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "logits_scaling": 8.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", "checkpoint_revision": "374ef54e020a3ce208c65e96d6213922a87d8952", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-2b-instruct/7636e0f2047e8e94e6b2.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.015625, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "logits_scaling": 8.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", "checkpoint_revision": "374ef54e020a3ce208c65e96d6213922a87d8952", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-2b-instruct/d4d13c6078baabc442f6.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.015625, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "logits_scaling": 8.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", "checkpoint_revision": "374ef54e020a3ce208c65e96d6213922a87d8952", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-8b-instruct/1b9e75e43d2171fdcbe3.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.0078125, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12800, "logits_scaling": 16.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "ibm-granite/granite-3.1-8b-instruct", "checkpoint_revision": "3f05a1d007b2484bbf17593efe110bd5b9d67655", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-8b-instruct/c8aa18c18169e58375cc.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.0078125, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12800, "logits_scaling": 16.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "ibm-granite/granite-3.1-8b-instruct", "checkpoint_revision": "3f05a1d007b2484bbf17593efe110bd5b9d67655", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-8b-instruct/ca9c6df7836e6c423599.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.0078125, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12800, "logits_scaling": 16.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "ibm-granite/granite-3.1-8b-instruct", "checkpoint_revision": "3f05a1d007b2484bbf17593efe110bd5b9d67655", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-8b-instruct/f31af7350e7bac5d240b.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.0078125, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12800, "logits_scaling": 16.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "ibm-granite/granite-3.1-8b-instruct", "checkpoint_revision": "3f05a1d007b2484bbf17593efe110bd5b9d67655", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/granite/ibm-granite/granite-3.1-8b-instruct/f5835b29e7f91c3f95bc.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.0078125, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12800, "logits_scaling": 16.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "ibm-granite/granite-3.1-8b-instruct", "checkpoint_revision": "3f05a1d007b2484bbf17593efe110bd5b9d67655", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Llama-2-13b-hf/409469dd48ea340e2031.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-13b-hf", "checkpoint_revision": "5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Llama-2-7b-hf/678b8395e743df567a53.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-7b-hf", "checkpoint_revision": "01c7f73d771dfac7d292323805ebc428287df4f9", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Llama-3.2-1B/06646cc5b14dfa510412.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.2-1B", "checkpoint_revision": "4e20de362430cd3b72f300e6b0f18e50e7166e08", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "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": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Llama-3.2-3B/60cfa39a4231a8e3e393.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.2-3B", "checkpoint_revision": "13afe5124825b4f3751f836b40dafda64c1ed062", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 24, "num_hidden_layers": 28, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "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": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3-8B/c779aa50e0bee568e4f9.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B/1e202b999f7f54120fb6.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B/663199108a75cad3f73b.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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": 16, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B/6753026c17aa56168b84.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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": 8, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B/7f1cfbb1aa86ae8f2d64.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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": 1, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B/c485b9da6e019edad2e2.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B/e51e4db5bc6b4214ad42.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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": 32, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B/fd4509240ba482254c74.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "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": 8, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/mixtral/mistralai/Mixtral-8x22B-Instruct-v0.1/ee5d6533fd230838cb38.json

@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 65536, "model_type": "mixtral", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "mistralai/Mixtral-8x22B-Instruct-v0.1", "checkpoint_revision": "a46959a1a02a9247294f5e141a4f3270059c6b32", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 48, "num_experts_per_tok": 2, "num_hidden_layers": 56, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/mixtral/mistralai/Mixtral-8x7B-Instruct-v0.1/19742370314f41e4a816.json

@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mixtral", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "checkpoint_revision": "41bd4c9e7e4fb318ca40e721131d4933966c2cc1", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.02, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/mixtral/mistralai/Mixtral-8x7B-Instruct-v0.1/6bd3bc29b3fd676ee742.json

@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mixtral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "checkpoint_revision": "41bd4c9e7e4fb318ca40e721131d4933966c2cc1", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.02, "router_jitter_noise": 0.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/phi3/microsoft/Phi-3-mini-4k-instruct/fc781bb5c3bd12f434ea.json

@@ -0,0 +1 @@
+{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"}, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 2047, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32064}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/phi3/microsoft/phi-4/9c0876e5186a665fa260.json

@@ -0,0 +1 @@
+{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100265, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 17920, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "microsoft/phi-4", "checkpoint_revision": "187ef0342fff0eb3333be9f00389385e95ef0b61", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 10, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 10, "original_max_position_embeddings": 16384, "pad_token_id": 100349, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/phi3/microsoft/phi-4/adeaca1cb3780dbd2e09.json

@@ -0,0 +1 @@
+{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100265, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 17920, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "microsoft/phi-4", "checkpoint_revision": "187ef0342fff0eb3333be9f00389385e95ef0b61", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 10, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 10, "original_max_position_embeddings": 16384, "pad_token_id": 100349, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/499a6f3c535d93bcd8c9.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"_attn_implementation_autoset": true, "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": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77, "tensor_parallel_size": 1}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"_attn_implementation_autoset": true, "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": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77, "tensor_parallel_size": 1}, "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": "2.16.372.0+4a9b2326", "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, "tensor_parallel_size": 1}, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/7555805b6a593a366a21.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b53f0d2daef297d8794a.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/da9452c0fcbe80e153f5.json

@@ -0,0 +1 @@
+{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/0af73583385b26dcf000.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/6af26305eda23594815e.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/c7c2db71d0de15fb6862.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/unsloth/Llama-3.2-1B-Instruct/08c70e54d07a8a28e136.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", "checkpoint_revision": "9b58d4a36161a1e49ecf0a69d20b2736fef8e438", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096}, "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": 128004, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "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": true, "torch_dtype": "bfloat16", "unsloth_fixed": true, "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/05491c46e49b1857820c.json

@@ -0,0 +1 @@
+{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/4e88b70b02777e345f13.json

@@ -0,0 +1 @@
+{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/f525ffd2f160d6993f6c.json

@@ -0,0 +1 @@
+{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/734242ffd55de3545f50.json

@@ -0,0 +1 @@
+{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/1fd7a329aeaaa0e24be7.json

@@ -0,0 +1 @@
+{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8, "initializer_range": 0.02, "intermediate_size": 16, "max_position_embeddings": 32768, "max_window_layers": 1, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": {"factor": 4.0, "original_max_position_embeddings": 32768, "rope_type": "yarn", "type": "yarn"}, "rope_theta": 1000000.0, "sliding_window": 131072, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/2c82c035621f7a01fd4d.json

@@ -0,0 +1 @@
+{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8, "initializer_range": 0.02, "intermediate_size": 16, "max_position_embeddings": 32768, "max_window_layers": 1, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": {"factor": 4.0, "original_max_position_embeddings": 32768, "rope_type": "yarn", "type": "yarn"}, "rope_theta": 1000000.0, "sliding_window": 131072, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/9d7846e07314372c51c8.json

@@ -0,0 +1 @@
+{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8, "initializer_range": 0.02, "intermediate_size": 16, "max_position_embeddings": 32768, "max_window_layers": 1, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": {"factor": 4.0, "original_max_position_embeddings": 32768, "rope_type": "yarn", "type": "yarn"}, "rope_theta": 1000000.0, "sliding_window": 131072, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}

neuronxcc-2.16.372.0+4a9b2326/MODULE_032f74178031f5ed3c74+613edded/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85bc88aae6303157b499a09533d1d5c0cec207dbb414612e42392dd2b2787b8
+oid sha256:47c09d3fa1d8555e140ca1118b0805031d13ec76530139b6cd851779eeaa63b7
 size 379904

neuronxcc-2.16.372.0+4a9b2326/MODULE_068ef074748718999f13+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.16.372.0+4a9b2326/MODULE_068ef074748718999f13+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4db209a482bf47e85f6fdaa653cf490bf3a08f633d3245452208b53c34d2036
+size 427799