Upload folder using huggingface_hub

.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.rknn filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,135 @@
+---
+base_model: ehdwns1516/bert-base-uncased_SWAG
+library_name: rk-transformers
+model_name: bert-base-uncased_SWAG
+tags:
+- rknn
+- rockchip
+- npu
+- rk-transformers
+- rk3588
+---
+# bert-base-uncased_SWAG (RKNN2)
+
+> This is an RKNN-compatible version of the [ehdwns1516/bert-base-uncased_SWAG](https://huggingface.co/ehdwns1516/bert-base-uncased_SWAG) 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:** [ehdwns1516/bert-base-uncased_SWAG](https://huggingface.co/ehdwns1516/bert-base-uncased_SWAG)
+- **Target Platform:** rk3588
+- **rknn-toolkit2 Version:** 2.3.2
+- **rk-transformers Version:** 0.3.0
+
+### Available Model Files
+
+| Model File | Optimization Level | Quantization | File Size |
+| :--------- | :----------------- | :----------- | :-------- |
+| [model.rknn](./model.rknn) | 0 | float16 | 235.4 MB |
+
+## Usage
+
+### Installation
+
+Install `rk-transformers` with inference dependencies to use this model:
+
+```bash
+pip install rk-transformers[inference]
+```
+
+#### RK-Transformers API
+
+```python
+import numpy as np
+from rktransformers import RKModelForMultipleChoice
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("rk-transformers/bert-base-uncased_SWAG")
+model = RKModelForMultipleChoice.from_pretrained(
+    "rk-transformers/bert-base-uncased_SWAG",
+    platform="rk3588",
+    core_mask="auto",
+)
+
+prompt = "In Italy, pizza is served in slices."
+choice0 = "It is eaten with a fork and knife."
+choice1 = "It is eaten while held in the hand."
+choice2 = "It is blended into a smoothie."
+choice3 = "It is folded into a taco."
+
+encoding = tokenizer(
+    [prompt, prompt, prompt, prompt], [choice0, choice1, choice2, choice3], return_tensors="np", padding=True
+)
+inputs = {k: np.expand_dims(v, 0) for k, v in encoding.items()}
+
+outputs = model(**inputs)
+logits = outputs.logits
+print(logits.shape)
+```
+
+## Configuration
+
+The full configuration for all exported RKNN models is available in the [config.json](./config.json) file.
+
+</details>
+
+---
+# ehdwns1516/bert-base-uncased_SWAG
+
+* This model has been trained as a [SWAG dataset](https://huggingface.co/ehdwns1516/bert-base-uncased_SWAG).
+
+* Sentence Inference Multiple Choice DEMO: [Ainize DEMO](https://main-sentence-inference-multiple-choice-ehdwns1516.endpoint.ainize.ai/)
+
+* Sentence Inference Multiple Choice API: [Ainize API](https://ainize.web.app/redirect?git_repo=https://github.com/ehdwns1516/sentence_inference_multiple_choice)
+
+## Overview
+
+Language model: [bert-base-uncased](https://huggingface.co/bert-base-uncased)
+
+Language: English
+
+Training data: [SWAG dataset](https://huggingface.co/datasets/swag)
+
+Code: See [Ainize Workspace](https://ainize.ai/workspace/create?imageId=hnj95592adzr02xPTqss&git=https://github.com/ehdwns1516/Multiple_choice_SWAG_finetunning)
+
+## Usage
+## In Transformers
+
+```
+from transformers import AutoTokenizer, AutoModelForMultipleChoice
+  
+tokenizer = AutoTokenizer.from_pretrained("ehdwns1516/bert-base-uncased_SWAG")
+
+model = AutoModelForMultipleChoice.from_pretrained("ehdwns1516/bert-base-uncased_SWAG")
+
+def run_model(candicates_count, context: str, candicates: list[str]):
+    assert len(candicates) == candicates_count, "you need " + candicates_count + " candidates"
+    choices_inputs = []
+    for c in candicates:
+        text_a = ""  # empty context
+        text_b = context + " " + c
+        inputs = tokenizer(
+            text_a,
+            text_b,
+            add_special_tokens=True,
+            max_length=128,
+            padding="max_length",
+            truncation=True,
+            return_overflowing_tokens=True,
+        )
+        choices_inputs.append(inputs)
+
+    input_ids = torch.LongTensor([x["input_ids"] for x in choices_inputs])
+    output = model(input_ids=input_ids)
+
+    return {"result": candicates[torch.argmax(output.logits).item()]}
+
+items = list()
+count = 4 # candicates count
+context = "your context"
+for i in range(int(count)):
+    items.append("sentence")
+
+result = run_model(count, context, items)
+```

config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "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",
+  "rknn": {
+    "model.rknn": {
+      "batch_size": 1,
+      "custom_string": null,
+      "dynamic_input": null,
+      "float_dtype": "float16",
+      "inputs_yuv_fmt": null,
+      "max_seq_length": 512,
+      "mean_values": null,
+      "model_input_names": [
+        "input_ids",
+        "attention_mask",
+        "token_type_ids"
+      ],
+      "opset": 19,
+      "optimization": {
+        "compress_weight": false,
+        "enable_flash_attention": true,
+        "model_pruning": false,
+        "optimization_level": 0,
+        "remove_reshape": false,
+        "remove_weight": false,
+        "sparse_infer": false
+      },
+      "quantization": {
+        "auto_hybrid_cos_thresh": 0.98,
+        "auto_hybrid_euc_thresh": null,
+        "dataset_columns": null,
+        "dataset_name": null,
+        "dataset_size": 128,
+        "dataset_split": null,
+        "dataset_subset": null,
+        "do_quantization": false,
+        "quant_img_RGB2BGR": false,
+        "quantized_algorithm": "normal",
+        "quantized_dtype": "w8a8",
+        "quantized_hybrid_level": 0,
+        "quantized_method": "channel"
+      },
+      "rktransformers_version": "0.3.0",
+      "single_core_mode": false,
+      "std_values": null,
+      "target_platform": "rk3588",
+      "task": "multiple-choice",
+      "task_kwargs": null
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.rknn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0676ec0732cec396f32659ac0e4060778791cb4e9647a482d52ab7c7da9612cc
+size 246809028

rknn.json

@@ -0,0 +1,47 @@
+{
+    "model.rknn": {
+        "rktransformers_version": "0.2.0",
+        "model_input_names": [
+            "input_ids",
+            "attention_mask",
+            "token_type_ids"
+        ],
+        "batch_size": 1,
+        "max_seq_length": 512,
+        "num_choices": 4,
+        "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": 19,
+        "task": "multiple-choice",
+        "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
+        }
+    }
+}

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "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]"
+}