Text Classification
Transformers
Safetensors
modernbert
code
language-identification
multi-label
llm-guard
encoder
text-embeddings-inference
Instructions to use Accuknoxtechnologies/CodeLanguage-Encoder-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Accuknoxtechnologies/CodeLanguage-Encoder-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Accuknoxtechnologies/CodeLanguage-Encoder-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Accuknoxtechnologies/CodeLanguage-Encoder-v1") model = AutoModelForSequenceClassification.from_pretrained("Accuknoxtechnologies/CodeLanguage-Encoder-v1") - Notebooks
- Google Colab
- Kaggle
add eval metrics json
Browse files- eval_metrics.json +42 -0
eval_metrics.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"n": 500,
|
| 3 |
+
"threshold": 0.5,
|
| 4 |
+
"is_valid_accuracy": 0.976,
|
| 5 |
+
"category_set_accuracy": 0.904,
|
| 6 |
+
"micro_f1": 0.9520426287744227,
|
| 7 |
+
"macro_f1": 0.9495788769189172,
|
| 8 |
+
"per_language_f1": {
|
| 9 |
+
"Python": 0.9803921568627451,
|
| 10 |
+
"JavaScript": 0.8627450980392157,
|
| 11 |
+
"Java": 1.0,
|
| 12 |
+
"C": 1.0,
|
| 13 |
+
"C++": 0.9583333333333334,
|
| 14 |
+
"C#": 0.95,
|
| 15 |
+
"Go": 0.95,
|
| 16 |
+
"Rust": 1.0,
|
| 17 |
+
"Kotlin": 1.0,
|
| 18 |
+
"Swift": 0.9387755102040817,
|
| 19 |
+
"Ruby": 0.9767441860465116,
|
| 20 |
+
"R": 0.9629629629629629,
|
| 21 |
+
"Scala": 0.8205128205128205,
|
| 22 |
+
"Perl": 0.9473684210526315,
|
| 23 |
+
"Lua": 0.9375,
|
| 24 |
+
"Bash": 0.8125,
|
| 25 |
+
"PowerShell": 0.9433962264150944,
|
| 26 |
+
"Batch": 0.9642857142857143,
|
| 27 |
+
"SQL": 1.0,
|
| 28 |
+
"Dockerfile": 0.9545454545454546,
|
| 29 |
+
"YAML": 0.9523809523809523,
|
| 30 |
+
"Makefile": 0.9767441860465116,
|
| 31 |
+
"Terraform": 0.95,
|
| 32 |
+
"AWK": 0.9259259259259259,
|
| 33 |
+
"jq": 0.9743589743589743
|
| 34 |
+
},
|
| 35 |
+
"latency_ms_per_example": {
|
| 36 |
+
"mean": 2.45145196095109,
|
| 37 |
+
"p95": 4.068814963102341,
|
| 38 |
+
"device": "cuda:0"
|
| 39 |
+
},
|
| 40 |
+
"base_model": "jhu-clsp/mmBERT-base",
|
| 41 |
+
"epochs": 3
|
| 42 |
+
}
|