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.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.1") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add report benchmark_cpu.json
Browse files- reports/benchmark_cpu.json +20 -20
reports/benchmark_cpu.json
CHANGED
|
@@ -13,34 +13,34 @@
|
|
| 13 |
"d_model": 128,
|
| 14 |
"heads": 4,
|
| 15 |
"d_ff": 384,
|
| 16 |
-
"single_latency_ms": 0.
|
| 17 |
-
"single_per_second":
|
| 18 |
"batch_size": 8,
|
| 19 |
-
"batch_latency_ms": 1.
|
| 20 |
-
"batch_per_second":
|
| 21 |
"peak_vram_mb": null,
|
| 22 |
"val": {
|
| 23 |
"threshold": 0.5,
|
| 24 |
-
"accuracy": 0.
|
| 25 |
-
"precision": 0.
|
| 26 |
-
"recall": 0.
|
| 27 |
-
"f1": 0.
|
| 28 |
-
"tp":
|
| 29 |
-
"fp":
|
| 30 |
-
"tn":
|
| 31 |
-
"fn":
|
| 32 |
"total": 6585
|
| 33 |
},
|
| 34 |
"test": {
|
| 35 |
"threshold": 0.5,
|
| 36 |
-
"accuracy": 0.
|
| 37 |
-
"precision": 0.
|
| 38 |
-
"recall": 0.
|
| 39 |
-
"f1": 0.
|
| 40 |
-
"tp":
|
| 41 |
-
"fp":
|
| 42 |
-
"tn":
|
| 43 |
-
"fn":
|
| 44 |
"total": 6496
|
| 45 |
},
|
| 46 |
"probe_set": {
|
|
|
|
| 13 |
"d_model": 128,
|
| 14 |
"heads": 4,
|
| 15 |
"d_ff": 384,
|
| 16 |
+
"single_latency_ms": 0.54,
|
| 17 |
+
"single_per_second": 1868.0,
|
| 18 |
"batch_size": 8,
|
| 19 |
+
"batch_latency_ms": 1.39,
|
| 20 |
+
"batch_per_second": 5738.0,
|
| 21 |
"peak_vram_mb": null,
|
| 22 |
"val": {
|
| 23 |
"threshold": 0.5,
|
| 24 |
+
"accuracy": 0.8552771450265756,
|
| 25 |
+
"precision": 0.8563469956227616,
|
| 26 |
+
"recall": 0.7842565597667639,
|
| 27 |
+
"f1": 0.8187178999429333,
|
| 28 |
+
"tp": 2152,
|
| 29 |
+
"fp": 361,
|
| 30 |
+
"tn": 3480,
|
| 31 |
+
"fn": 592,
|
| 32 |
"total": 6585
|
| 33 |
},
|
| 34 |
"test": {
|
| 35 |
"threshold": 0.5,
|
| 36 |
+
"accuracy": 0.8589901477832512,
|
| 37 |
+
"precision": 0.8594941790445604,
|
| 38 |
+
"recall": 0.7909124492057629,
|
| 39 |
+
"f1": 0.8237783762985764,
|
| 40 |
+
"tp": 2141,
|
| 41 |
+
"fp": 350,
|
| 42 |
+
"tn": 3439,
|
| 43 |
+
"fn": 566,
|
| 44 |
"total": 6496
|
| 45 |
},
|
| 46 |
"probe_set": {
|