Text Classification
Transformers
Safetensors
modernbert
agent-safety
tool-calling
long-context
distillation
Eval Results (legacy)
text-embeddings-inference
Instructions to use ProCreations/auto-0.4b-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProCreations/auto-0.4b-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ProCreations/auto-0.4b-2")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ProCreations/auto-0.4b-2") model = AutoModelForSequenceClassification.from_pretrained("ProCreations/auto-0.4b-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval/iteration-1/preview-kd_b_aug-step-1737-benchmark.json from ProCreations/auto-0.4b-2: direct link, hf CLI and curl.
- Browser
- Download file 2.27 kB
-
https://huggingface.co/ProCreations/auto-0.4b-2/resolve/main/eval/iteration-1/preview-kd_b_aug-step-1737-benchmark.json
- Command line
-
hf download hf://ProCreations/auto-0.4b-2/eval/iteration-1/preview-kd_b_aug-step-1737-benchmark.json
-
curl -L -o preview-kd_b_aug-step-1737-benchmark.json https://huggingface.co/ProCreations/auto-0.4b-2/resolve/main/eval/iteration-1/preview-kd_b_aug-step-1737-benchmark.json
2.27 kB
| { | |
| "export": "/home/user/checkpoints/auto04-v3/kd_b_aug/step-1737", | |
| "sha256": "bca2d2614055c7dc43d6d9f059446691c343b5bf0ca5271cfe6f29f507cc201d", | |
| "time": "2026-09-10T23:11:27Z", | |
| "overall": { | |
| "n": 3000, | |
| "accuracy": 0.9683333333333334, | |
| "balanced_accuracy": 0.9687913886221715, | |
| "f1_deny": 0.9664192294096854, | |
| "auroc": 0.9949238884581236, | |
| "nll": 0.09748464604243104, | |
| "false_approve_rate": 0.02426837972876517, | |
| "false_deny_rate": 0.03814884302689181, | |
| "false_approve_count": 34, | |
| "false_deny_count": 61, | |
| "deny_count": 1401, | |
| "approve_count": 1599, | |
| "threshold": 0.5, | |
| "brier": 0.02513362427571565, | |
| "accuracy_ci95": [ | |
| 0.9614436833643786, | |
| 0.9740251283295661 | |
| ] | |
| }, | |
| "long_16k_64k": { | |
| "n": 239, | |
| "accuracy": 0.9623430962343096, | |
| "balanced_accuracy": 0.962188113260443, | |
| "f1_deny": 0.9635627530364372, | |
| "auroc": 0.9942879170171012, | |
| "nll": 0.10733518996547653, | |
| "false_approve_rate": 0.032520325203252036, | |
| "false_deny_rate": 0.04310344827586207, | |
| "false_approve_count": 4, | |
| "false_deny_count": 5, | |
| "deny_count": 123, | |
| "approve_count": 116, | |
| "threshold": 0.5, | |
| "brier": 0.03148497052555311, | |
| "accuracy_ci95": [ | |
| 0.9299945026243701, | |
| 0.9800642701784192 | |
| ] | |
| }, | |
| "paired_vs_published": { | |
| "fixed": 31, | |
| "new_errors": 29, | |
| "published_correct": 2903, | |
| "this_correct": 2905 | |
| }, | |
| "lang": { | |
| "English": { | |
| "n": 2104, | |
| "errors": 53 | |
| }, | |
| "French": { | |
| "n": 91, | |
| "errors": 1 | |
| }, | |
| "German": { | |
| "n": 82, | |
| "errors": 3 | |
| }, | |
| "Hindi": { | |
| "n": 78, | |
| "errors": 9 | |
| }, | |
| "Italian": { | |
| "n": 97, | |
| "errors": 0 | |
| }, | |
| "Japanese": { | |
| "n": 112, | |
| "errors": 5 | |
| }, | |
| "Korean": { | |
| "n": 97, | |
| "errors": 4 | |
| }, | |
| "Mandarin Chinese": { | |
| "n": 83, | |
| "errors": 5 | |
| }, | |
| "Portuguese": { | |
| "n": 77, | |
| "errors": 3 | |
| }, | |
| "Russian": { | |
| "n": 90, | |
| "errors": 5 | |
| }, | |
| "Spanish": { | |
| "n": 89, | |
| "errors": 7 | |
| } | |
| }, | |
| "difficulty": { | |
| "easy": { | |
| "n": 870, | |
| "errors": 14 | |
| }, | |
| "hard": { | |
| "n": 1065, | |
| "errors": 49 | |
| }, | |
| "medium": { | |
| "n": 1065, | |
| "errors": 32 | |
| } | |
| } | |
| } | |