Text Classification
Transformers
Safetensors
lfm2
feature-extraction
betterwright
accessibility
browser-agent
reranking
long-context
custom_code
Instructions to use ProCreations/betterwright-encoder-350m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProCreations/betterwright-encoder-350m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ProCreations/betterwright-encoder-350m", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ProCreations/betterwright-encoder-350m", trust_remote_code=True) model = AutoModel.from_pretrained("ProCreations/betterwright-encoder-350m", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload relevance_config.json with huggingface_hub
Browse files- relevance_config.json +16 -0
relevance_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema": "betterwright-relevance-config-v1",
|
| 3 |
+
"relevance_threshold": 0.25,
|
| 4 |
+
"confidence_threshold": 0.45,
|
| 5 |
+
"max_retained_fraction": 1.0,
|
| 6 |
+
"max_ranked_lines": 0,
|
| 7 |
+
"strategy": "coarse-ref-context",
|
| 8 |
+
"max_ranked_windows": 8,
|
| 9 |
+
"ref_context_lines": 3,
|
| 10 |
+
"window_chars": 1800,
|
| 11 |
+
"minimum_validation_recall": 0.999,
|
| 12 |
+
"minimum_validation_perfect_task_recall": 0.995,
|
| 13 |
+
"validated_max_chars": 10000,
|
| 14 |
+
"fallback_on_error": true,
|
| 15 |
+
"model": "ProCreations/betterwright-encoder-350m"
|
| 16 |
+
}
|