Starling-LM-7B-alpha
berkeley-nest/Starling-LM-7B-alpha
7BStarling4 Heretic artifacts1 measured conversions9.8K downloads
Best version90.0Pareto
ChiKoi7/Starling-LM-7B-alpha-Hereticby ChiKoi7 · Heretic v1.0.1 · GGUF, SAFETENSORS
- KL divergence
- 0.010
- Refusals
- 19/100
- Refusal rate
- 19%
- Downloads
- 9.8K
Evidence from the model card
| Refusals | 19/100 | | KL divergence | 0.01 |
Metrics published by the author. Why this ranks first.
All measured versions
Higher score is better. One row per ablation attempt; artifacts of the same attempt are grouped under it.
| # | Author | Params | KL | Refusals | Score | Evidence | Downloads |
|---|---|---|---|---|---|---|---|
| 1 | ChiKoi7 | 7B | 0.010 | 19/10019% | 90.0 | BestParetoGGUFSAFETENSORS | 9.8K |
All artifacts (4)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| Starling-LM-7B-alpha-Heretic-i1-GGUF mradermacher | quant | GGUFIQ1_M | inheritedKL 0.010 | 5.7K | 2025-12-12 |
| Starling-LM-7B-alpha-Heretic-GGUF ChiKoi7 | heretic | GGUF | published (weak match)KL 0.010 | 2.7K | 2025-12-11 |
| Starling-LM-7B-alpha-Heretic-GGUF mradermacher | quant | GGUFIQ4_XS | inheritedKL 0.010 | 1.3K | 2025-12-12 |
| Starling-LM-7B-alpha-Heretic ChiKoi7 | heretic | SAFETENSORS | published (weak match)KL 0.010 | 79 | 2025-12-11 |