Text Classification
Transformers
ONNX
English
roberta
int8
optimum
ONNXRuntime
text-embeddings-inference
Instructions to use minuva/MiniLMv2-agentflow-v2-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use minuva/MiniLMv2-agentflow-v2-onnx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="minuva/MiniLMv2-agentflow-v2-onnx")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("minuva/MiniLMv2-agentflow-v2-onnx") model = AutoModelForSequenceClassification.from_pretrained("minuva/MiniLMv2-agentflow-v2-onnx", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,9 @@ license: apache-2.0
|
|
| 5 |
---
|
| 6 |
# LLM agent flow text classification
|
| 7 |
|
| 8 |
-
This model identifies common LLM agent events and patterns within the conversation flow.
|
|
|
|
|
|
|
| 9 |
|
| 10 |
It is ONNX quantized and is a fined-tune of [MiniLMv2-L6-H384](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large).
|
| 11 |
The base model can be found [here](https://huggingface.co/minuva/MiniLMv2-agentflow-v2)
|
|
|
|
| 5 |
---
|
| 6 |
# LLM agent flow text classification
|
| 7 |
|
| 8 |
+
This model identifies common LLM agent events and patterns within the conversation flow.
|
| 9 |
+
Such events include an apology, where the LLM acknowledges a mistake.
|
| 10 |
+
The flow labels can serve as foundational elements for sophisticated LLM analytics.
|
| 11 |
|
| 12 |
It is ONNX quantized and is a fined-tune of [MiniLMv2-L6-H384](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large).
|
| 13 |
The base model can be found [here](https://huggingface.co/minuva/MiniLMv2-agentflow-v2)
|