Text Classification
Transformers
ONNX
Safetensors
llama
safety
content-moderation
multi-label
multilingual
tiny-language-model
from-scratch
distilled
text-embeddings-inference
Instructions to use KucLab/Barist.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.5")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.5") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download reports/benchmark.md from KucLab/Barist.5: direct link, hf CLI and curl.
- Browser
- Download file 1.03 kB
-
https://huggingface.co/KucLab/Barist.5/resolve/main/reports/benchmark.md
- Command line
-
hf download hf://KucLab/Barist.5/reports/benchmark.md
-
curl -L -o benchmark.md https://huggingface.co/KucLab/Barist.5/resolve/main/reports/benchmark.md
1.03 kB
| # Barist.1 — Benchmark | |
| Generated by `scripts/benchmark.py`. | |
| ## Hardware | |
| - Device: `AMD Radeon Graphics` (cuda) | |
| - torch: `2.13.0+rocm7.1` | |
| - Python: `3.12.12` | |
| - OS: `Linux-7.1.7-100.fc43.x86_64-x86_64-with-glibc2.43` | |
| ## Model | |
| | Property | Value | | |
| | --- | --- | | |
| | Parameters | 903,552 | | |
| | Checkpoint size | 3.45 MB | | |
| | Vocabulary | 2048 | | |
| | Context | 4096 tokens | | |
| | Input limit | 4000 characters | | |
| | Layers / d_model / heads / d_ff | 3 / 128 / 4 / 384 | | |
| ## Inference | |
| | Metric | Value | | |
| | --- | --- | | |
| | Single text latency | 1.04 ms | | |
| | Single text throughput | 958.1 texts/s | | |
| | Batch of 8 latency | 1.23 ms | | |
| | Batched throughput | 6490.0 texts/s | | |
| | Peak VRAM (inference) | 84.7 MB | | |
| ## Accuracy | |
| | Split | Rows | Accuracy | F1 | Precision | Recall | | |
| | --- | --- | --- | --- | --- | --- | | |
| | val | 6585 | 0.8535 | 0.8175 | 0.8498 | 0.7875 | | |
| | test | 6496 | 0.8570 | 0.8225 | 0.8519 | 0.7950 | | |
| | probe (hand-written) | 97 | 0.9897 | 0.9882 | 0.9767 | 1.0000 | | |
| The probe set is hand-written and absent from all training data. | |