Synchronizing local compiler cache.
Browse files- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/08f3910c4c9ee92dd0b5.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/1df6ca3f978199f21b51.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/a8dd88894399c5adbb18.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/gpt2/4a0fe61f82a71cd05cad.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/hf-internal-testing/tiny-random-gpt2/128c453e38853624fabd.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1449b39ac1e921360157.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/hf-internal-testing/tiny-random-gpt2/55118cfe0a06efa3274d.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/8c0d6cba2fb47a55008c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/b6c5a29aa4bcb76f8ac2.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/ed70c60ab514455dd70c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/62bc6e1795da82df4ed8.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/67c426c2522557c10d6d.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ccffca7a6d62a6acf92b.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/0f9698e2c5baf3bcdfbc.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/6badd54902699de07371.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/bc110f8f1779b9da99c5.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/0e81573d0a8ba5fb3e07.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/967118f91af6f3fa17b1.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/acc73d16175f74b1d60c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/89fd3144c76c7f1e83f4.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/a401bc08f15a803a3530.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/da9636523ea3ccf92d40.json +1 -0
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/08f3910c4c9ee92dd0b5.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "_task": "text-generation", "apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "dtype": "float32", "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/1df6ca3f978199f21b51.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "_task": "text-generation", "apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "dtype": "float32", "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/a8dd88894399c5adbb18.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "_task": "text-generation", "apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "dtype": "float32", "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/gpt2/4a0fe61f82a71cd05cad.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "gpt2", "_task": "text-generation", "activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "embd_pdrop": 0.1, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "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, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/hf-internal-testing/tiny-random-gpt2/128c453e38853624fabd.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-gpt2", "_task": "text-generation", "activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "embd_pdrop": 0.1, "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": "fp16", "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": 100, "task": "text-generation"}, "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/0.2.0.dev1/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1449b39ac1e921360157.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-gpt2", "_task": "text-generation", "activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "embd_pdrop": 0.1, "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": "fp16", "batch_size": 2, "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": 100, "task": "text-generation"}, "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/0.2.0.dev1/inference/gpt2/hf-internal-testing/tiny-random-gpt2/55118cfe0a06efa3274d.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-gpt2", "_task": "text-generation", "activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "embd_pdrop": 0.1, "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": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "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/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/8c0d6cba2fb47a55008c.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "llamafactory/tiny-random-Llama-3", "_task": "text-generation", "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "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, "task": "text-generation"}, "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, "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/b6c5a29aa4bcb76f8ac2.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "llamafactory/tiny-random-Llama-3", "_task": "text-generation", "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "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, "task": "text-generation"}, "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, "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/ed70c60ab514455dd70c.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "llamafactory/tiny-random-Llama-3", "_task": "text-generation", "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "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, "task": "text-generation"}, "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, "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/62bc6e1795da82df4ed8.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "dacorvo/tiny-random-MistralForCausalLM", "_task": "text-generation", "architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/67c426c2522557c10d6d.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "dacorvo/tiny-random-MistralForCausalLM", "_task": "text-generation", "architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ccffca7a6d62a6acf92b.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "dacorvo/tiny-random-MistralForCausalLM", "_task": "text-generation", "architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/0f9698e2c5baf3bcdfbc.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "dacorvo/Mixtral-tiny", "_task": "text-generation", "architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "head_dim": 32, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/6badd54902699de07371.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "dacorvo/Mixtral-tiny", "_task": "text-generation", "architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "head_dim": 32, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/bc110f8f1779b9da99c5.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "dacorvo/Mixtral-tiny", "_task": "text-generation", "architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "head_dim": 32, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/0e81573d0a8ba5fb3e07.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "_remove_final_layer_norm": false, "_task": "text-generation", "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "3f3f2ee1e499cb7ad89b877068684fdc9d9513c3", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/967118f91af6f3fa17b1.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "_remove_final_layer_norm": false, "_task": "text-generation", "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "3f3f2ee1e499cb7ad89b877068684fdc9d9513c3", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/acc73d16175f74b1d60c.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "_remove_final_layer_norm": false, "_task": "text-generation", "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "3f3f2ee1e499cb7ad89b877068684fdc9d9513c3", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/89fd3144c76c7f1e83f4.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "yujiepan/phi-4-tiny-random", "_task": "text-generation", "architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "embd_pdrop": 0.0, "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, "task": "text-generation"}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "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, "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/a401bc08f15a803a3530.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "yujiepan/phi-4-tiny-random", "_task": "text-generation", "architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "embd_pdrop": 0.0, "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, "task": "text-generation"}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "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, "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/da9636523ea3ccf92d40.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "yujiepan/phi-4-tiny-random", "_task": "text-generation", "architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "embd_pdrop": 0.0, "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, "task": "text-generation"}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "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, "use_cache": true, "vocab_size": 100352}
|