Qwen-SEA-LION-v4-8B-VL
aisingapore/Qwen-SEA-LION-v4-8B-VL
8BQwen3 Heretic artifacts1 measured conversions8.8K downloads
Best version80.0Pareto
MagicalAlchemist/Qwen-SEA-LION-v4-8B-VL-Magic_decensoredby MagicalAlchemist · Heretic v1.1.0 · GGUF, SAFETENSORS
- KL divergence
- 0.387
- Refusals
- 12/100
- Refusal rate
- 12%
- Downloads
- 8.8K
Evidence from the model card
| KL divergence | 0.3868 | | Refusals | 12/100 |
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 | MagicalAlchemist | 8B | 0.387 | 12/10012% | 80.0 | BestParetoGGUFSAFETENSORS | 8.8K |
All artifacts (3)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| Qwen-SEA-LION-v4-8B-VL-Magic_decensored-i1-GGUF mradermacher | quant | GGUFIQ1_M | inheritedKL 0.387 | 6K | 2026-01-29 |
| Qwen-SEA-LION-v4-8B-VL-Magic_decensored-GGUF mradermacher | quant | GGUFIQ4_XS | inheritedKL 0.387 | 2.2K | 2026-01-29 |
| Qwen-SEA-LION-v4-8B-VL-Magic_decensored MagicalAlchemist | heretic | SAFETENSORS | published (weak match)KL 0.387 | 540 | 2026-01-25 |