Model Card for answer-finder-v1-S-en
This model is a question answering model developed by Sinequa. It produces two lists of logit scores corresponding to the start token and end token of an answer.
Model name: answer-finder-v1-S-en
Supported Languages
The model was trained and tested in the following languages:
- English
Scores
| Metric | Value |
|---|---|
| F1 Score on SQuAD v2 with Hugging Face evaluation pipeline | 79.4 |
| F1 Score on SQuAD v2 with Haystack evaluation pipeline | 79.5 |
Inference Time
| GPU | Quantization type | Batch size 1 | Batch size 32 |
|---|---|---|---|
| NVIDIA A10 | FP16 | 1 ms | 10 ms |
| NVIDIA A10 | FP32 | 3 ms | 43 ms |
| NVIDIA T4 | FP16 | 2 ms | 22 ms |
| NVIDIA T4 | FP32 | 5 ms | 130 ms |
| NVIDIA L4 | FP16 | 2 ms | 12 ms |
| NVIDIA L4 | FP32 | 5 ms | 62 ms |
Note that the Answer Finder models are only used at query time.
Gpu Memory usage
| Quantization type | Memory |
|---|---|
| FP16 | 300 MiB |
| FP32 | 550 MiB |
Note that GPU memory usage only includes how much GPU memory the actual model consumes on an NVIDIA T4 GPU with a batch size of 32. It does not include the fix amount of memory that is consumed by the ONNX Runtime upon initialization which can be around 0.5 to 1 GiB depending on the used GPU.
Requirements
- Minimal Sinequa version: 11.10.0
- Minimal Sinequa version for using FP16 models and GPUs with CUDA compute capability of 8.9+ (like NVIDIA L4): 11.11.0
Model Details
Overview
- Number of parameters: 33 million
- Base language model: microsoft/MiniLM-L12-H384-uncased
- Insensitive to casing and accents