MiniLMv2-goemotions-v2-onnx

MiniLMv2-goemotions-v2-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-goemotions-v2-onnx/README.md

@@ -0,0 +1,177 @@
+---
+datasets:
+- go_emotions
+language:
+- en
+library_name: transformers
+inference: false
+model-index:
+- name: text-classification-goemotions
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: go_emotions
+      type: multilabel_classification
+      config: simplified
+      split: test
+      args: simplified
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.482
+license: apache-2.0
+tags:
+- emotions
+- multi-class-classification
+- multi-label-classification
+- onnx
+- int8
+- emotion
+- ONNXRuntime
+---
+
+# Text Classification GoEmotions
+
+This a ONNX quantized model and is fined-tuned version of [MiniLMv2-L6-H384](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large) on the on the [go_emotions](https://huggingface.co/datasets/go_emotions) dataset using [tasinho/text-classification-goemotions](https://huggingface.co/tasinhoque/text-classification-goemotions) as teacher model.
+The original model can be found [here](https://huggingface.co/minuva/MiniLMv2-goemotions-v2)
+
+# 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-goemotions-v2-onnx', provider="CPUExecutionProvider")
+tokenizer = AutoTokenizer.from_pretrained('minuva/MiniLMv2-goemotions-v2-onnx', use_fast=True, model_max_length=256, truncation=True, padding='max_length')
+
+pipe = pipeline(task='text-classification', model=model, tokenizer=tokenizer, )
+texts = ["that's wrong", "can you please answer me?"]
+pipe(texts)
+# [{'label': 'anger', 'score': 0.9727636575698853},
+# {'label': 'love', 'score': 0.9874765276908875}]
+```
+# ONNX Runtime only
+
+A lighter solution for deployment
+
+
+## Installation
+```bash
+pip install tokenizers
+pip install onnxruntime
+git clone https://huggingface.co/minuva/MiniLMv2-goemotions-v2-onnx
+```
+
+## Run the Model
+
+```py
+import os
+import numpy as np
+import json
+
+from tokenizers import Tokenizer
+from onnxruntime import InferenceSession
+
+
+model_name = "minuva/MiniLMv2-goemotions-v2-onnx"
+
+tokenizer = Tokenizer.from_pretrained(model_name)
+tokenizer.enable_padding(
+    pad_token="<pad>",
+    pad_id=1,
+)
+tokenizer.enable_truncation(max_length=256)
+batch_size = 16
+
+texts = ["I am angry", "I feel in love"]
+outputs = []
+model = InferenceSession("MiniLMv2-goemotions-v2-onnx/model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])
+
+with open(os.path.join("MiniLMv2-goemotions-v2-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
+
+# [('anger', 0.9745745062828064), ('love', 0.9884329438209534)]
+```
+# Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 6e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+
+
+# Metrics (comparison with teacher model)
+
+| Teacher (params)    |   Student (params)     | Set         | Score (teacher)    |    Score (student)      |
+|--------------------|-------------|----------|--------| --------|
+| tasinhoque/text-classification-goemotions (355M) |      MiniLMv2-goemotions-v2-onnx (30M)   | Validation  | 0.514252 | 0.4780 |
+| tasinhoque/text-classification-goemotions (335M) |      MiniLMv2-goemotions-v2-onnx  (30M)  | Test  | 0.501937 |  0.482 |
+
+# Deployment
+
+Check out our [fast-nlp-text-emotion repository](https://github.com/minuva/fast-nlp-text-emotion) for a FastAPI based server to easily deploy this model on CPU devices.

MiniLMv2-goemotions-v2-onnx/config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "../output/minilmv2-roberta-v2-goemotions-opt",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "admiration",
+    "1": "amusement",
+    "2": "anger",
+    "3": "annoyance",
+    "4": "approval",
+    "5": "caring",
+    "6": "confusion",
+    "7": "curiosity",
+    "8": "desire",
+    "9": "disappointment",
+    "10": "disapproval",
+    "11": "disgust",
+    "12": "embarrassment",
+    "13": "excitement",
+    "14": "fear",
+    "15": "gratitude",
+    "16": "grief",
+    "17": "joy",
+    "18": "love",
+    "19": "nervousness",
+    "20": "optimism",
+    "21": "pride",
+    "22": "realization",
+    "23": "relief",
+    "24": "remorse",
+    "25": "sadness",
+    "26": "surprise",
+    "27": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "admiration": "0",
+    "amusement": "1",
+    "anger": "2",
+    "annoyance": "3",
+    "approval": "4",
+    "caring": "5",
+    "confusion": "6",
+    "curiosity": "7",
+    "desire": "8",
+    "disappointment": "9",
+    "disapproval": "10",
+    "disgust": "11",
+    "embarrassment": "12",
+    "excitement": "13",
+    "fear": "14",
+    "gratitude": "15",
+    "grief": "16",
+    "joy": "17",
+    "love": "18",
+    "nervousness": "19",
+    "neutral": "27",
+    "optimism": "20",
+    "pride": "21",
+    "realization": "22",
+    "relief": "23",
+    "remorse": "24",
+    "sadness": "25",
+    "surprise": "26"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

MiniLMv2-goemotions-v2-onnx/model_optimized_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594ac3bf3c82e2ea187e50982ea2f811ede5377eaad0c8ad23bc04ee8a2486c6
+size 30458927

MiniLMv2-goemotions-v2-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-goemotions-v2-onnx/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/minuva/MiniLMv2-goemotions-v2-onnx

MiniLMv2-goemotions-v2-onnx/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

MiniLMv2-goemotions-v2-onnx/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 64,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}