Zero-Shot Classification
Transformers
Safetensors
GGUF
English
decision-model
system-one
falcondec
lightdec
calibrated-decisions
multiple-choice
intent-classification
customer-support
natural-language-inference
code
guardrails
agents
selective-prediction
falconsai
model-surgeon
attested-lineage
Instructions to use Falconsai/LightDec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Falconsai/LightDec with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="Falconsai/LightDec")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Falconsai/LightDec", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload config.json with huggingface_hub
Browse files- config.json +6 -0
config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"falconsai.synthesized": true,
|
| 3 |
+
"num_hidden_layers": 22,
|
| 4 |
+
"falconsai.tool": "FALCONS.AI Model Surgeon V7.99",
|
| 5 |
+
"falconsai.attn_note": "attention kernel is chosen at load time (e.g. attn_implementation='flash_attention_2' on CUDA/ROCm hosts that have it); nothing in this file selects it"
|
| 6 |
+
}
|