Add Neuron-optimized files for microsoft/deberta-v3-large

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

Original model: [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large)
Task: fill-mask
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
+- fill-mask
+base_model: microsoft/deberta-v3-large
+---
+
+# Neuron-Optimized microsoft/deberta-v3-large
+
+This repository contains AWS Neuron-optimized files for [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large).
+
+## Model Details
+
+- **Base Model**: [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large)
+- **Task**: fill-mask
+- **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 NeuronModelForMaskedLM
+
+model = NeuronModelForMaskedLM.from_pretrained("badaoui/microsoft-deberta-v3-large-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: [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large)

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "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": "deberta-v2",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "static_batch_size": 1,
+    "static_sequence_length": 128,
+    "task": "fill-mask",
+    "tensor_parallel_size": 1
+  },
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "torchscript": true,
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05cd48bb2e97b3420eea2b57c54506021f67186e5f59d56f4e9d8b00564b2475
+size 1113745917

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}