Dolphin3.0-Llama3.1-8B
dphn/Dolphin3.0-Llama3.1-8B
8BLlama 3.16 Heretic artifacts1 measured conversions24.7K downloads
Best version99.6Pareto
anasali4151/llama3.1-heretic-unsensoredby anasali4151 · Heretic v1.3.0 · GGUF, SAFETENSORS
- KL divergence
- 0.0082
- Refusals
- 0/100
- Refusal rate
- 0%
- Downloads
- 24.7K
Evidence from the model card
| KL divergence | 0.0082 | | Refusals | 0/100 |
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 | anasali4151 | 8B | 0.0082 | 0/1000% | 99.6 | BestParetoGGUFSAFETENSORS | 24.7K |
All artifacts (6)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| llama3.1-heretic-unsensored-GGUF mradermacher | quant | GGUFIQ4_XS | inheritedKL 0.0082 | 12.2K | 2026-05-07 |
| llama3.1-heretic-unsensored-i1-GGUF mradermacher | quant | GGUFIQ1_M | inheritedKL 0.0082 | 11.8K | 2026-05-07 |
| llama3.1-heretic-unsensored anasali4151 | heretic | SAFETENSORS | published (weak match)KL 0.0082 | 502 | 2026-05-06 |
| llama3.1-heretic-unsensored Theright07 | heretic | SAFETENSORS | published (weak match)KL 0.0082 | 183 | 2026-06-02 |
| my-cool-model bigjake17x | heretic | SAFETENSORS | published (weak match)KL 0.0082 | 22 | 2026-09-28 |
| llama3.1-heretic-unsensored Vhicktour | heretic | SAFETENSORS | published (weak match)KL 0.0082 | 14 | 2026-09-24 |