Instructions to use qhoenix/zils-mini-onejev-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qhoenix/zils-mini-onejev-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="qhoenix/zils-mini-onejev-ft", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("qhoenix/zils-mini-onejev-ft", trust_remote_code=True) model = AutoModel.from_pretrained("qhoenix/zils-mini-onejev-ft", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
zils-mini-onejev-ft
A d3-mini decision body (Qwen/Qwen3.5-4B family) for the Zils subnet 127 mini pool.
Built by LoRA fine-tuning OmniJev OneJev1.5-4B (Apache-2.0) on the Zils d3-mini chassis with decision-style data from train splits of public datasets and newly written practice items, then averaging 50% current mini soup (torchcast-ai/torchcast-decision-4b + vllm-sr/d3-mini) / 50% fine-tune. Licensed under Apache-2.0; see LICENSE and NOTICE.
- Downloads last month
- 16