Instructions to use qhoenix/zils-lite-decision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qhoenix/zils-lite-decision with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="qhoenix/zils-lite-decision", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("qhoenix/zils-lite-decision", trust_remote_code=True) model = AutoModel.from_pretrained("qhoenix/zils-lite-decision", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
zils-lite-decision
A d3-lite decision body (Qwen/Qwen3.5-0.8B family) for the Zils subnet 127 lite pool.
Built by LoRA fine-tuning a uniform weight average of vllm-sr/d3-lite, Maincode/Matilda-Decision-v1-Edge and cribl-ai/cribl-decision-2-0.8B (all Apache-2.0) on public decision-style data (train splits of public classification/NLI/QA datasets and resolved public events), then averaging the result 50/50 with that base average. Licensed under Apache-2.0; see LICENSE and NOTICE for upstream attributions.
- Downloads last month
- 25