Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,11 @@ 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.rknn filter=lfs diff=lfs merge=lfs -text
+model_b1_s256.rknn filter=lfs diff=lfs merge=lfs -text
+model_b4_s256.rknn filter=lfs diff=lfs merge=lfs -text
+model_b4_s512.rknn filter=lfs diff=lfs merge=lfs -text
+rknn/model_o1.rknn filter=lfs diff=lfs merge=lfs -text
+rknn/model_o2.rknn filter=lfs diff=lfs merge=lfs -text
+rknn/model_o3.rknn filter=lfs diff=lfs merge=lfs -text
+rknn/model_w8a8.rknn filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,331 @@
+---
+language: en
+tags:
+- exbert
+- rknn
+- rockchip
+- npu
+- rk-transformers
+- rk3588
+license: apache-2.0
+model_name: bert-base-uncased
+base_model: google-bert/bert-base-uncased
+library_name: rk-transformers
+---
+# bert-base-uncased (RKNN2)
+
+> This is an RKNN-compatible version of the [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) model. It has been optimized for Rockchip NPUs using the [rk-transformers](https://github.com/emapco/rk-transformers) library.
+
+<details><summary>Click to see the RKNN model details and usage examples</summary>
+
+## Model Details
+
+- **Original Model:** [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased)
+- **Target Platform:** rk3588
+- **rknn-toolkit2 Version:** 2.3.2
+- **rk-transformers Version:** 0.1.0
+
+### Available Model Files
+
+| Model File | Optimization Level | Quantization | File Size |
+| :--------- | :----------------- | :----------- | :-------- |
+| [model.rknn](./model.rknn) | 0 | float16 | 261.1 MB |
+| [model_b1_s256.rknn](./model_b1_s256.rknn) | 0 | float16 | 258.4 MB |
+| [model_b4_s256.rknn](./model_b4_s256.rknn) | 0 | float16 | 270.3 MB |
+| [model_b4_s512.rknn](./model_b4_s512.rknn) | 0 | float16 | 280.5 MB |
+| [rknn/model_o1.rknn](./rknn/model_o1.rknn) | 1 | float16 | 261.1 MB |
+| [rknn/model_o2.rknn](./rknn/model_o2.rknn) | 2 | float16 | 261.1 MB |
+| [rknn/model_o3.rknn](./rknn/model_o3.rknn) | 3 | float16 | 261.1 MB |
+| [rknn/model_w8a8.rknn](./rknn/model_w8a8.rknn) | 0 | w8a8 | 133.6 MB |
+
+## Usage
+
+### Installation
+
+Install `rk-transformers` to use this model:
+
+```bash
+pip install rk-transformers
+```
+
+#### RKTransformers API
+
+```python
+from rktransformers import RKRTModelForFeatureExtraction
+from transformers import AutoTokenizer
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("rk-transformers/bert-base-uncased")
+model = RKRTModelForFeatureExtraction.from_pretrained(
+    "rk-transformers/bert-base-uncased",
+    platform="rk3588",
+    core_mask="auto",
+)
+
+# Tokenize and run inference
+inputs = tokenizer(
+    ["Sample text for encoding"],
+    padding="max_length",
+    max_length=256,
+    truncation=True,
+    return_tensors="np"
+)
+
+outputs = model(**inputs)
+print(outputs.shape)
+
+# Load specific optimized/quantized model file
+model = RKRTModelForFeatureExtraction.from_pretrained(
+    "rk-transformers/bert-base-uncased",
+    platform="rk3588",
+    file_name="rknn/model_w8a8.rknn"
+)
+```
+
+## Configuration
+
+The full configuration for all exported RKNN models is available in the [rknn.json](./rknn.json) file.
+
+</details>
+
+# BERT base model (uncased)
+
+Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
+[this paper](https://arxiv.org/abs/1810.04805) and first released in
+[this repository](https://github.com/google-research/bert). This model is uncased: it does not make a difference
+between english and English.
+
+Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by
+the Hugging Face team.
+
+## Model description
+
+BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
+was pretrained on the raw texts only, with no humans labeling them in any way (which is why it can use lots of
+publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
+was pretrained with two objectives:
+
+- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
+  the entire masked sentence through the model and has to predict the masked words. This is different from traditional
+  recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
+  GPT which internally masks the future tokens. It allows the model to learn a bidirectional representation of the
+  sentence.
+- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
+  they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
+  predict if the two sentences were following each other or not.
+
+This way, the model learns an inner representation of the English language that can then be used to extract features
+useful for downstream tasks: if you have a dataset of labeled sentences, for instance, you can train a standard
+classifier using the features produced by the BERT model as inputs.
+
+## Model variations
+
+BERT has originally been released in base and large variations, for cased and uncased input text. The uncased models also strips out an accent markers.  
+Chinese and multilingual uncased and cased versions followed shortly after.  
+Modified preprocessing with whole word masking has replaced subpiece masking in a following work, with the release of two models.  
+Other 24 smaller models are released afterward.  
+
+The detailed release history can be found on the [google-research/bert readme](https://github.com/google-research/bert/blob/master/README.md) on github.
+
+| Model | #params | Language |
+|------------------------|--------------------------------|-------|
+| [`bert-base-uncased`](https://huggingface.co/bert-base-uncased) | 110M   | English |
+| [`bert-large-uncased`](https://huggingface.co/bert-large-uncased)              | 340M    | English | sub 
+| [`bert-base-cased`](https://huggingface.co/bert-base-cased)        | 110M    | English |
+| [`bert-large-cased`](https://huggingface.co/bert-large-cased) | 340M    |  English |
+| [`bert-base-chinese`](https://huggingface.co/bert-base-chinese) | 110M    | Chinese |
+| [`bert-base-multilingual-cased`](https://huggingface.co/bert-base-multilingual-cased) | 110M | Multiple |
+| [`bert-large-uncased-whole-word-masking`](https://huggingface.co/bert-large-uncased-whole-word-masking) | 340M | English |
+| [`bert-large-cased-whole-word-masking`](https://huggingface.co/bert-large-cased-whole-word-masking) | 340M | English |
+
+## Intended uses & limitations
+
+You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
+be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=bert) to look for
+fine-tuned versions of a task that interests you.
+
+Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
+to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
+generation you should look at model like GPT2.
+
+### How to use
+
+You can use this model directly with a pipeline for masked language modeling:
+
+```python
+>>> from transformers import pipeline
+>>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
+>>> unmasker("Hello I'm a [MASK] model.")
+
+[{'sequence': "[CLS] hello i'm a fashion model. [SEP]",
+  'score': 0.1073106899857521,
+  'token': 4827,
+  'token_str': 'fashion'},
+ {'sequence': "[CLS] hello i'm a role model. [SEP]",
+  'score': 0.08774490654468536,
+  'token': 2535,
+  'token_str': 'role'},
+ {'sequence': "[CLS] hello i'm a new model. [SEP]",
+  'score': 0.05338378623127937,
+  'token': 2047,
+  'token_str': 'new'},
+ {'sequence': "[CLS] hello i'm a super model. [SEP]",
+  'score': 0.04667217284440994,
+  'token': 3565,
+  'token_str': 'super'},
+ {'sequence': "[CLS] hello i'm a fine model. [SEP]",
+  'score': 0.027095865458250046,
+  'token': 2986,
+  'token_str': 'fine'}]
+```
+
+Here is how to use this model to get the features of a given text in PyTorch:
+
+```python
+from transformers import BertTokenizer, BertModel
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model = BertModel.from_pretrained("bert-base-uncased")
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+```
+
+and in TensorFlow:
+
+```python
+from transformers import BertTokenizer, TFBertModel
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model = TFBertModel.from_pretrained("bert-base-uncased")
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='tf')
+output = model(encoded_input)
+```
+
+### Limitations and bias
+
+Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
+predictions:
+
+```python
+>>> from transformers import pipeline
+>>> unmasker = pipeline('fill-mask', model='bert-base-uncased')
+>>> unmasker("The man worked as a [MASK].")
+
+[{'sequence': '[CLS] the man worked as a carpenter. [SEP]',
+  'score': 0.09747550636529922,
+  'token': 10533,
+  'token_str': 'carpenter'},
+ {'sequence': '[CLS] the man worked as a waiter. [SEP]',
+  'score': 0.0523831807076931,
+  'token': 15610,
+  'token_str': 'waiter'},
+ {'sequence': '[CLS] the man worked as a barber. [SEP]',
+  'score': 0.04962705448269844,
+  'token': 13362,
+  'token_str': 'barber'},
+ {'sequence': '[CLS] the man worked as a mechanic. [SEP]',
+  'score': 0.03788609802722931,
+  'token': 15893,
+  'token_str': 'mechanic'},
+ {'sequence': '[CLS] the man worked as a salesman. [SEP]',
+  'score': 0.037680890411138535,
+  'token': 18968,
+  'token_str': 'salesman'}]
+
+>>> unmasker("The woman worked as a [MASK].")
+
+[{'sequence': '[CLS] the woman worked as a nurse. [SEP]',
+  'score': 0.21981462836265564,
+  'token': 6821,
+  'token_str': 'nurse'},
+ {'sequence': '[CLS] the woman worked as a waitress. [SEP]',
+  'score': 0.1597415804862976,
+  'token': 13877,
+  'token_str': 'waitress'},
+ {'sequence': '[CLS] the woman worked as a maid. [SEP]',
+  'score': 0.1154729500412941,
+  'token': 10850,
+  'token_str': 'maid'},
+ {'sequence': '[CLS] the woman worked as a prostitute. [SEP]',
+  'score': 0.037968918681144714,
+  'token': 19215,
+  'token_str': 'prostitute'},
+ {'sequence': '[CLS] the woman worked as a cook. [SEP]',
+  'score': 0.03042375110089779,
+  'token': 5660,
+  'token_str': 'cook'}]
+```
+
+This bias will also affect all fine-tuned versions of this model.
+
+## Training data
+
+The BERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
+unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
+headers).
+
+## Training procedure
+
+### Preprocessing
+
+The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
+then of the form:
+
+```
+[CLS] Sentence A [SEP] Sentence B [SEP]
+```
+
+With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus, and in
+the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
+consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
+"sentences" has a combined length of less than 512 tokens.
+
+The details of the masking procedure for each sentence are the following:
+- 15% of the tokens are masked.
+- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
+- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
+- In the 10% remaining cases, the masked tokens are left as is.
+
+### Pretraining
+
+The model was trained on 4 cloud TPUs in Pod configuration (16 TPU chips total) for one million steps with a batch size
+of 256. The sequence length was limited to 128 tokens for 90% of the steps and 512 for the remaining 10%. The optimizer
+used is Adam with a learning rate of 1e-4, \\(\beta_{1} = 0.9\\) and \\(\beta_{2} = 0.999\\), a weight decay of 0.01,
+learning rate warmup for 10,000 steps and linear decay of the learning rate after.
+
+## Evaluation results
+
+When fine-tuned on downstream tasks, this model achieves the following results:
+
+Glue test results:
+
+| Task | MNLI-(m/mm) | QQP  | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE  | Average |
+|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
+|      | 84.6/83.4   | 71.2 | 90.5 | 93.5  | 52.1 | 85.8  | 88.9 | 66.4 | 79.6    |
+
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{DBLP:journals/corr/abs-1810-04805,
+  author    = {Jacob Devlin and
+               Ming{-}Wei Chang and
+               Kenton Lee and
+               Kristina Toutanova},
+  title     = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language
+               Understanding},
+  journal   = {CoRR},
+  volume    = {abs/1810.04805},
+  year      = {2018},
+  url       = {http://arxiv.org/abs/1810.04805},
+  archivePrefix = {arXiv},
+  eprint    = {1810.04805},
+  timestamp = {Tue, 30 Oct 2018 20:39:56 +0100},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}
+```
+
+<a href="https://huggingface.co/exbert/?model=bert-base-uncased">
+	<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
+</a>

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

coreml/fill-mask/float32_model.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "9D749A46-ADA0-43CA-B5C2-8E722B91F41E": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "D545B13F-2D5E-4CFB-BFF1-C10E9EFD70DA": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "9D749A46-ADA0-43CA-B5C2-8E722B91F41E"
+}

model.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82e76cd0d3c4bb14ba88aa6a0e2843f2e904cb65ca955ba5f465f0b5c9304d7
+size 273830854

model_b1_s256.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c3d5aa68001fd22f0f66cda6c8e04cbdad931a430d5d0802e8bed325d72d36
+size 270969670

model_b4_s256.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abad409b4f884e6a49c4d1a2144dd90f5a70ec9a615014da2fc62747fb755457
+size 283424646

model_b4_s512.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c777bf44463b5738af0693ce5a5fe54cf4f4516c6bff68e7979f89d8c11ee80
+size 294075782

rknn.json

@@ -0,0 +1,350 @@
+{
+    "model.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 512,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "fill-mask",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 0,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "rknn/model_o1.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 512,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "fill-mask",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 1,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "rknn/model_o2.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 512,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "fill-mask",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 2,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "rknn/model_o3.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 512,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "fill-mask",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 3,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "rknn/model_w8a8.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 512,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "fill-mask",
+        "quantization": {
+            "do_quantization": true,
+            "dataset_name": "sentence-transformers/natural-questions",
+            "dataset_subset": null,
+            "dataset_size": 2048,
+            "dataset_split": [
+                "train"
+            ],
+            "dataset_columns": [
+                "answer"
+            ],
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 0,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "model_b4_s512.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 4,
+        "max_seq_length": 512,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "fill-mask",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 0,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "model_b1_s256.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 256,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "auto",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 0,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    },
+    "model_b4_s256.rknn": {
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 4,
+        "max_seq_length": 256,
+        "float_dtype": "float16",
+        "target_platform": "rk3588",
+        "single_core_mode": false,
+        "mean_values": null,
+        "std_values": null,
+        "custom_string": null,
+        "inputs_yuv_fmt": null,
+        "dynamic_input": null,
+        "opset": 18,
+        "task": "auto",
+        "quantization": {
+            "do_quantization": false,
+            "dataset_name": null,
+            "dataset_subset": null,
+            "dataset_size": 128,
+            "dataset_split": null,
+            "dataset_columns": null,
+            "quantized_dtype": "w8a8",
+            "quantized_algorithm": "normal",
+            "quantized_method": "channel",
+            "quantized_hybrid_level": 0,
+            "quant_img_RGB2BGR": false,
+            "auto_hybrid_cos_thresh": 0.98,
+            "auto_hybrid_euc_thresh": null
+        },
+        "optimization": {
+            "optimization_level": 0,
+            "enable_flash_attention": true,
+            "remove_weight": false,
+            "compress_weight": false,
+            "remove_reshape": false,
+            "sparse_infer": false,
+            "model_pruning": false
+        }
+    }
+}

rknn/model_o1.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82e76cd0d3c4bb14ba88aa6a0e2843f2e904cb65ca955ba5f465f0b5c9304d7
+size 273830854

rknn/model_o2.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82e76cd0d3c4bb14ba88aa6a0e2843f2e904cb65ca955ba5f465f0b5c9304d7
+size 273830854

rknn/model_o3.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8436f148c0cc91d78ba562aac653601a3a69e7cc11d70922efa107437a750ebd
+size 273830854

rknn/model_w8a8.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b35b9cf8db6760f45b2fd9cc700e5bd88f8af73a69ecc87fe70799aa8ecd5b0
+size 140070675

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}