Qwen-SEA-LION-v4-4B-VL
aisingapore/Qwen-SEA-LION-v4-4B-VL
4BQwen3 Heretic artifacts1 measured conversions9.8K downloads
Best version96.1Pareto
MagicalAlchemist/Qwen-SEA-LION-v4-4B-VL-Magic_decensoredby MagicalAlchemist · Heretic v1.1.0 · GGUF, SAFETENSORS
- KL divergence
- 0.039
- Refusals
- 4/100
- Refusal rate
- 4%
- Downloads
- 9.8K
Evidence from the model card
| KL divergence | 0.0388 | | Refusals | 4/100 |
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 | 4B | 0.039 | 4/1004% | 96.1 | BestParetoGGUFSAFETENSORS | 9.8K |
All artifacts (3)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| Qwen-SEA-LION-v4-4B-VL-Magic_decensored-i1-GGUF mradermacher | quant | GGUFIQ1_M | inheritedKL 0.039 | 8.3K | 2026-02-15 |
| Qwen-SEA-LION-v4-4B-VL-Magic_decensored-GGUF mradermacher | quant | GGUFIQ4_XS | inheritedKL 0.039 | 1.1K | 2026-01-28 |
| Qwen-SEA-LION-v4-4B-VL-Magic_decensored MagicalAlchemist | heretic | SAFETENSORS | published (weak match)KL 0.039 | 388 | 2026-01-25 |