d1-qwen-0.6b decision model
d1-qwen-0.6b is an independent Qwen text decision starter. Read its per-candidate context limit, trained head and published test results.
By Grizzlykw · Hugging Face package release: 4 Nov 2026
An independent Qwen3-0.6B text decision starter with a frozen backbone and a trained 1,025-parameter compatibility head. It uses no LiquidAI weights. Each question-option pair repeats the state in its own input row, so candidate count adds work and memory. The package includes weights, code, splits and a training report.
Quick answers
What is d1-qwen-0.6b by Grizzlykw?
d1-qwen-0.6b: An independent Qwen3-0.6B text decision starter with a frozen backbone and a trained 1,025-parameter compatibility head.
Who makes d1-qwen-0.6b?
d1-qwen-0.6b: Grizzlykw
Facts
- Inputs
- Text or JSON; choice, independent multiple choice, yes/no and score
- Context
- 512 tokens per candidate row; longer input raises an error
- Licence
- Apache-2.0
Claims and sources
- The saved report gives trained accuracy 0.5715 versus baseline 0.386 on 2,000 test decisions across Banking77, SST5, GoEmotions, BoolQ and AG News. The checkpoint and temperature were selected on a separate calibration split. These task results do not validate arbitrary questions or other domains. vendor reportedsource
Links
Source: Card and standalone package → Source: Training report →
Related projects
No related projects are listed in the registry.