Llama-3.1-8B-Lexi-Uncensored-V2
Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
8BLlama 3.16 Heretic artifacts2 measured conversions32.5K downloads
Best version98.3Pareto
Spaceballs/Llama-3.1-8B-Lexi-Uncensored-V2-hereticby Spaceballs · Heretic v1.3.0 · SAFETENSORS
- KL divergence
- 0.015
- Refusals
- 2/100
- Refusal rate
- 2%
- Downloads
- 214
Evidence from the model card
| KL divergence | 0.0152 | | Refusals | 2/100 |
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 | Spaceballs | 8B | 0.015 | 2/1002% | 98.3 | BestParetoSAFETENSORS | 214 |
| 2 | ChiKoi7 | 8B | 0.020 | 2/1002% | 98.0 | GGUFSAFETENSORS | 27.3K |
All artifacts (6)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-i1-GGUF mradermacher | quant | GGUFIQ1_M | inheritedKL 0.020 | 14.6K | 2025-12-11 |
| Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-GGUF ChiKoi7 | quant | GGUF | published (weak match)KL 0.020 | 7.3K | 2025-12-11 |
| Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-GGUF mradermacher | quant | GGUFIQ4_XS | inheritedKL 0.020 | 5.1K | 2025-12-11 |
| Llama-3.1-8B-Lexi-Uncensored-V2-heretic-GGUF Spaceballs | quant | GGUFQ4_K_M | none | 5K | 2026-06-05 |
| Llama-3.1-8B-Lexi-Uncensored-V2-Heretic ChiKoi7 | heretic | SAFETENSORS | published (weak match)KL 0.020 | 289 | 2025-12-11 |
| Llama-3.1-8B-Lexi-Uncensored-V2-heretic Spaceballs | heretic | SAFETENSORS | published (weak match)KL 0.015 | 214 | 2026-06-05 |
1 artifact inherit metrics from their parent conversion or publish none.