Add Neuron-optimized files for DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT

🤖 Neuron Export Bot: Adding AWS Neuron-optimized model files.

Original model: [DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT](https://huggingface.co/DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT)
Task: text-classification
Generated by: [badaoui](https://huggingface.co/badaoui)
Generated using: [Optimum Neuron Compiler Space](https://huggingface.co/spaces/optimum/neuron-export)

These files have been pre-compiled for AWS Neuron devices (Inferentia/Trainium) and should provide improved inference performance.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.neuron filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+tags:
+- neuron
+- optimized
+- aws-neuron
+- text-classification
+base_model: DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT
+---
+
+# Neuron-Optimized DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT
+
+This repository contains AWS Neuron-optimized files for [DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT](https://huggingface.co/DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT).
+
+## Model Details
+
+- **Base Model**: [DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT](https://huggingface.co/DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT)
+- **Task**: text-classification
+- **Optimization**: AWS Neuron compilation
+- **Generated by**: [badaoui](https://huggingface.co/badaoui)
+- **Generated using**: [Optimum Neuron Compiler Space](https://huggingface.co/spaces/optimum/neuron-export)
+
+## Usage
+
+This model has been optimized for AWS Neuron devices (Inferentia/Trainium). To use it:
+
+```python
+from optimum.neuron import NeuronModelForSequenceClassification
+
+model = NeuronModelForSequenceClassification.from_pretrained("badaoui/DAMO-NLP-SG-zero-shot-classify-SSTuning-ALBERT-neuron")
+```
+
+## Performance
+
+These files are pre-compiled for AWS Neuron devices and should provide improved inference performance compared to the original model when deployed on Inferentia or Trainium instances.
+
+## Original Model
+
+For the original model, training details, and more information, please visit: [DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT](https://huggingface.co/DAMO-NLP-SG/zero-shot-classify-SSTuning-ALBERT)

config.json

@@ -0,0 +1,100 @@
+{
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "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": "albert",
+    "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": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "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,
+  "vocab_size": 30000
+}

model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6147aa43a1083e5fdd433d3253d85c430bac39776ca7374d97a657a4846a8e9b
+size 399035069

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizerFast",
+  "unk_token": "<unk>"
+}