MiniLMv2-userflow-v2-onnx

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

@@ -0,0 +1,210 @@
+---
+language:
+- en
+
+inference: false
+tags:
+  - text-classification
+  - onnx
+  - int8
+  - optimum
+  - multi-class-classification
+  - ONNXRuntime
+license: apache-2.0
+---
+
+# LLM user flow classification
+
+This model identifies common events and patterns within the conversation flow. 
+Such events include, for example, complaint, when a user expresses dissatisfaction.
+The flow labels can serve as foundational elements for sophisticated LLM analytics.
+
+It is ONNX quantized and is a fined-tune of [MiniLMv2-L6-H384](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large).
+The base model can be found [here](https://huggingface.co/minuva/MiniLMv2-userflow-v2)
+
+This model is used *only* for the user texts. For the LLM texts in the dialog use this [agent model](https://huggingface.co/minuva/MiniLMv2-agentflow-v2-onnx). 
+
+
+# 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-userflow-v2-onnx', provider="CPUExecutionProvider")
+tokenizer = AutoTokenizer.from_pretrained('minuva/MiniLMv2-userflow-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': 'model_wrong_or_try_again', 'score': 0.9737648367881775},
+# {'label': 'user_wants_agent_to_answer', 'score': 0.9105103015899658}]
+```
+
+
+# ONNX Runtime only
+
+A lighter solution for deployment
+
+## Installation 
+
+```bash
+pip install tokenizers
+pip install onnxruntime
+git clone https://huggingface.co/minuva/MiniLMv2-userflow-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-userflow-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 = ["that's wrong", "can you please answer me?"]
+
+
+outputs = []
+model = InferenceSession("MiniLMv2-userflow-v2-onnx/model_optimized_quantized.onnx", providers=['CPUExecutionProvider'])
+
+with open(os.path.join("MiniLMv2-userflow-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
+#[('model_wrong_or_try_again', 0.9737648367881775),
+# ('user_wants_agent_to_answer', 0.9105103015899658)]
+```
+
+# Categories Explanation
+
+<details>
+  <summary>Click to expand!</summary>
+  
+  - OTHER: Responses that do not fit into any predefined categories or are outside the scope of the specific interaction types listed.
+
+  - agrees_praising_thanking: When the user agrees with the provided information, offers praise, or expresses gratitude.
+
+  - asks_source: The user requests the source of the information or the basis for the answer provided.
+
+  - continue: Indicates a prompt for the conversation to proceed or continue without a specific directional change.
+
+   - continue_or_finnish_code: Signals either to continue with the current line of discussion or code execution, or to conclude it.
+
+  - improve_or_modify_answer: The user requests an improvement or modification to the provided answer.
+
+  -  lack_of_understandment: Reflects the user's or agent confusion or lack of understanding regarding the information provided.
+
+   - model_wrong_or_try_again: Indicates that the model's response was incorrect or unsatisfactory, suggesting a need to attempt another answer.
+
+   - more_listing_or_expand: The user requests further elaboration, expansion from the given list by the agent.
+
+   - repeat_answers_or_question: The need to reiterate a previous answer or question.
+
+  - request_example: The user asks for examples to better understand the concept or answer provided.
+
+  - user_complains_repetition: The user notes that the information or responses are repetitive, indicating a need for new or different content.
+
+  - user_doubts_answer: The user expresses skepticism or doubt regarding the accuracy or validity of the provided answer.
+
+  - user_goodbye: The user says goodbye to the agent.
+
+  - user_reminds_question: The user reiterates the question.
+
+  - user_wants_agent_to_answer: The user explicitly requests a response from the agent, when the agent refuses to do so.
+
+  - user_wants_explanation: The user seeks an explanation behind the information or answer provided.
+
+  - user_wants_more_detail: Indicates the user's desire for more comprehensive or detailed information on the topic.
+
+  - user_wants_shorter_longer_answer: The user requests that the answer be condensed or expanded to better meet their informational needs.
+
+  - user_wants_simplier_explanation: The user seeks a simpler, more easily understood explanation.
+
+  - user_wants_yes_or_no: The user is asking for a straightforward affirmative or negative answer, without additional detail or explanation.
+</details>
+
+<br>
+
+
+# Metrics in our private test dataset
+| Model (params)    |    Loss      |    Accuracy |  F1 |
+|--------------------|-------------|----------|--------| 
+| minuva/MiniLMv2-userflow-v2 (33M) |   0.6738 | 0.7236 | 0.7313 |
+| minuva/MiniLMv2-userflow-v2-onnx (33M) |   - | 0.7195 | 0.7189 |
+
+# Deployment
+
+Check our [llm-flow-classification repository](https://github.com/minuva/llm-flow-classification) for a FastAPI and ONNX based server to deploy this model on CPU devices.

MiniLMv2-userflow-v2-onnx/config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "../output/MiniLMv2-userflow-v2-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": "OTHER",
+    "1": "agrees_praising_thanking",
+    "2": "asks_source",
+    "3": "continue",
+    "4": "continue_or_finnish_code",
+    "5": "improve_or_modify_answer",
+    "6": "lack_of_understandment",
+    "7": "model_wrong_or_try_again",
+    "8": "more_listing_or_expand",
+    "9": "repeat_answers_or_question",
+    "10": "request_example",
+    "11": "user_complains_repetition",
+    "12": "user_doubts_answer",
+    "13": "user_goodbye",
+    "14": "user_reminds_question",
+    "15": "user_wants_agent_to_answer",
+    "16": "user_wants_explanation",
+    "17": "user_wants_more_detail",
+    "18": "user_wants_shorter_longer_answer",
+    "19": "user_wants_simplier_explanation",
+    "20": "user_wants_yes_or_no"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "OTHER": 0,
+    "agrees_praising_thanking": 1,
+    "asks_source": 2,
+    "continue": 3,
+    "continue_or_finnish_code": 4,
+    "improve_or_modify_answer": 5,
+    "lack_of_understandment": 6,
+    "model_wrong_or_try_again": 7,
+    "more_listing_or_expand": 8,
+    "repeat_answers_or_question": 9,
+    "request_example": 10,
+    "user_complains_repetition": 11,
+    "user_doubts_answer": 12,
+    "user_goodbye": 13,
+    "user_reminds_question": 14,
+    "user_wants_agent_to_answer": 15,
+    "user_wants_explanation": 16,
+    "user_wants_more_detail": 17,
+    "user_wants_shorter_longer_answer": 18,
+    "user_wants_simplier_explanation": 19,
+    "user_wants_yes_or_no": 20
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

MiniLMv2-userflow-v2-onnx/model_optimized_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0228740a10c2c7788ee554be779a63aa246fee20736b9a1d713660e41a78f3
+size 30456211

MiniLMv2-userflow-v2-onnx/ort_config.json

@@ -0,0 +1,35 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.16.1",
+  "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-userflow-v2-onnx/source.txt

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

MiniLMv2-userflow-v2-onnx/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

MiniLMv2-userflow-v2-onnx/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "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": 512,
+  "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>"
+}