Model profile
Belle 7B 2M
2023-03-20release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 2 of 7 behavior components. Its strongest relative result is Chinese Bias Benchmark for Question Answering (bias_score, #3 of 10); its weakest is CValues (score, #9 of 10).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗BelleGroup/BELLE-7B-2M
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| Chinese Bias Benchmark for Question Answeringbias_score | #3 / 10 | 0.3884 | ↓ lower | Source ↗official | |
| CValuesscore | #9 / 10 | 72.8 | ↑ higher | Source ↗official |