Synchronizing local compiler cache of anandkumar-107/Intent_Classifier

.gitattributes

@@ -12850,3 +12850,4 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_3652085762323541144+bad9cf09/model.neff f
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_8484172002609230754+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_8487175863267765630+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_9217004124000298644+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_6e01324b55b5e1bee011/model.neuron filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1/bert/anandkumar-107/Intent_Classifier/6e01324b55b5e1bee011.json

@@ -0,0 +1,65 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "anandkumar-107/Intent_Classifier",
+  "_task": "text-classification",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "assistant command",
+    "1": "automation",
+    "2": "chat",
+    "3": "factual recall",
+    "4": "new fact",
+    "5": "reasoning",
+    "6": "task management"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "assistant command": 0,
+    "automation": 1,
+    "chat": 2,
+    "factual recall": 3,
+    "new fact": 4,
+    "reasoning": 5,
+    "task management": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.21.18209.0+043b1bf7",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": false,
+    "float_dtype": "fp32",
+    "inline_weights_to_neff": true,
+    "instance_type": "inf2",
+    "int_dtype": "int64",
+    "model_type": "bert",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "static_batch_size": 1,
+    "static_sequence_length": 128,
+    "task": "text-classification",
+    "tensor_parallel_size": 1
+  },
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_6e01324b55b5e1bee011/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "assistant command",
+    "1": "automation",
+    "2": "chat",
+    "3": "factual recall",
+    "4": "new fact",
+    "5": "reasoning",
+    "6": "task management"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "assistant command": 0,
+    "automation": 1,
+    "chat": 2,
+    "factual recall": 3,
+    "new fact": 4,
+    "reasoning": 5,
+    "task management": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.21.18209.0+043b1bf7",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": false,
+    "float_dtype": "fp32",
+    "inline_weights_to_neff": true,
+    "instance_type": "inf2",
+    "int_dtype": "int64",
+    "model_type": "bert",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "static_batch_size": 1,
+    "static_sequence_length": 128,
+    "task": "text-classification",
+    "tensor_parallel_size": 1
+  },
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "torchscript": true,
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_6e01324b55b5e1bee011/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98f6e00220c8c922e77e4f3d40d563867844080464b51a492fbbce20fd79f26
+size 67253757

neuronxcc-2.21.18209.0+043b1bf7/MODULE_6e01324b55b5e1bee011/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_6e01324b55b5e1bee011/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}