Zero-Shot Classification
Transformers
Safetensors
English
qwen3
text-generation
assay
decision-model
calibrated
conformal-prediction
text-classification
structured-output
text-generation-inference
Instructions to use Berk/assay-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Berk/assay-0.6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="Berk/assay-0.6b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Berk/assay-0.6b") model = AutoModelForCausalLM.from_pretrained("Berk/assay-0.6b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Lead with abstention: it is what makes this different
Verified signature4c99ddc -
Surface under zero-shot-classification with complete metadata
Verified signature1bf5099
-
write rope_theta so transformers 4 reads the right RoPE base
Verified signature74d9020 -
Tokenizer config that transformers 4 can load
Verified signature4fcc3db -
Upload folder using huggingface_hub
Verified signaturefd9b5e7
-
Upload folder using huggingface_hub
Verified signaturefe60bbe -
Upload folder using huggingface_hub
Verified signature7b5ff00 -
Upload folder using huggingface_hub
Verified signatureaf014dd -
Upload folder using huggingface_hub
Verified signaturecd06044 -
Upload folder using huggingface_hub
Verified signaturec6d4f7d -
initial commit
Verified signature4d48f2e