MiniLMv2-toxic-jigsaw-onnx

MiniLMv2-toxic-jigsaw-onnx/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

MiniLMv2-toxic-jigsaw-onnx/README.md

@@ -0,0 +1,159 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+  - toxic
+  - toxicity
+  - hate speech
+  - offensive language
+  - onnx
+  - int8
+  - multi-class-classification
+  - multi-label-classification
+  - ONNXRuntime
+
+inference: false
+---
+
+# Text Classification Toxicity
+
+This is a quantized onnx model and is a fined-tuned version of [MiniLMv2-L6-H384](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large) on the on the [Jigsaw 1st Kaggle competition](https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge) dataset using [unitary/toxic-bert](https://huggingface.co/unitary/toxic-bert) as teacher model.
+The original model can be found [here](https://huggingface.co/minuva/MiniLMv2-toxic-jigsaw)
+
+
+# Optimum
+
+## Installation
+
+Install from source: 
+```bash
+python -m pip install optimum[onnxruntime]@git+https://github.com/huggingface/optimum.git
+```
+
+
+## Run the Model
+```py
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer, pipeline
+
+model = ORTModelForSequenceClassification.from_pretrained('minuva/MiniLMv2-toxic-jigsaw-onnx', provider="CPUExecutionProvider")
+tokenizer = AutoTokenizer.from_pretrained('minuva/MiniLMv2-toxic-jigsaw-onnx', use_fast=True, model_max_length=256, truncation=True, padding='max_length')
+
+pipe = pipeline(task='text-classification', model=model, tokenizer=tokenizer, )
+texts = ["This is pure trash",]
+pipe(texts)
+# [{'label': 'toxic', 'score': 0.736885666847229}]
+```
+
+# ONNX Runtime only
+
+A lighter solution for deployment
+
+
+## Installation
+
+```bash
+pip install tokenizers
+pip install onnxruntime
+git clone https://huggingface.co/minuva/MiniLMv2-toxic-jigsaw-onnx
+```
+
+
+## Load the Model
+
+```py
+import os
+import numpy as np
+import json
+
+from tokenizers import Tokenizer
+from onnxruntime import InferenceSession
+
+
+model_name = "minuva/MiniLMv2-toxic-jigsaw-onnx"
+tokenizer = Tokenizer.from_pretrained(model_name)
+tokenizer.enable_padding()
+tokenizer.enable_truncation(max_length=256)
+batch_size = 16
+
+texts = ["This is pure trash",]
+outputs = []
+model = InferenceSession("MiniLMv2-toxic-jigsaw-onnx/model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])
+
+with open(os.path.join("MiniLMv2-toxic-jigsaw-onnx", "config.json"), "r") as f:
+            config = json.load(f)
+
+output_names = [output.name for output in model.get_outputs()]
+input_names = [input.name for input in model.get_inputs()]
+
+for subtexts in np.array_split(np.array(texts), len(texts) // batch_size + 1):
+            encodings = tokenizer.encode_batch(list(subtexts))
+            inputs = {
+                "input_ids": np.vstack(
+                    [encoding.ids for encoding in encodings],
+                ),
+                "attention_mask": np.vstack(
+                    [encoding.attention_mask for encoding in encodings],
+                ),
+                "token_type_ids": np.vstack(
+                    [encoding.type_ids for encoding in encodings],
+                ),
+            }
+
+            for input_name in input_names:
+                if input_name not in inputs:
+                    raise ValueError(f"Input name {input_name} not found in inputs")
+
+            inputs = {input_name: inputs[input_name] for input_name in input_names}
+            output = np.squeeze(
+                np.stack(
+                    model.run(output_names=output_names, input_feed=inputs)
+                ),
+                axis=0,
+            )
+            outputs.append(output)
+
+outputs = np.concatenate(outputs, axis=0)
+scores = 1 / (1 + np.exp(-outputs))
+results = []
+for item in scores:
+    labels = []
+    scores = []
+    for idx, s in enumerate(item):
+        labels.append(config["id2label"][str(idx)])
+        scores.append(float(s))
+    results.append({"labels": labels, "scores": scores})
+
+res = []
+
+for result in results:
+    joined = list(zip(result['labels'], result['scores']))
+    max_score = max(joined, key=lambda x: x[1])    
+    res.append(max_score)
+
+res
+# [('toxic', 0.736885666847229)]
+```
+
+# Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 6e-05
+- train_batch_size: 48
+- eval_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- warmup_ratio: 0.1
+
+
+# Metrics (comparison with teacher model)
+
+| Teacher (params)    |   Student (params)     | Set  (metric)     | Score (teacher)    |    Score (student)      |
+|--------------------|-------------|----------|--------| --------|
+| unitary/toxic-bert (110M) |  MiniLMv2-toxic-jigsaw-onnx (23M)  | Test (ROC_AUC)  | 0.98636 |  0.98130 |
+
+# Deployment
+
+Check out [fast-nlp-text-toxicity repository](https://github.com/minuva/fast-nlp-text-toxicity) for a FastAPI based server to deploy this model in CPU devices.

MiniLMv2-toxic-jigsaw-onnx/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "../output/MiniLM-L6-toxic-all-labels-opt",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "toxic",
+    "1": "severe_toxic",
+    "2": "obscene",
+    "3": "threat",
+    "4": "insult",
+    "5": "identity_hate"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "identity_hate": "5",
+    "insult": "4",
+    "obscene": "2",
+    "severe_toxic": "1",
+    "threat": "3",
+    "toxic": "0"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

MiniLMv2-toxic-jigsaw-onnx/model_optimized_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd9dfb48cad802ac8f7cd789e1294f1f0b22d532797bd41f5a11694e3c269a0
+size 22864978

MiniLMv2-toxic-jigsaw-onnx/ort_config.json

@@ -0,0 +1,35 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.14.1",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": false,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "transformers_version": "4.30.0",
+  "use_external_data_format": false
+}

MiniLMv2-toxic-jigsaw-onnx/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/minuva/MiniLMv2-toxic-jigsaw-onnx

MiniLMv2-toxic-jigsaw-onnx/special_tokens_map.json

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

MiniLMv2-toxic-jigsaw-onnx/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}