LFM2.5-230M
LiquidAI/LFM2.5-230M
0.2BLFM3 Heretic artifacts1 measured conversions2.9K downloads
Best version92.4Pareto
saidutta69/LFM2.5-230M-hereticby saidutta69 · Heretic v1.4.0 · GGUF, SAFETENSORS
- KL divergence
- 0.055
- Refusals
- 10/100
- Refusal rate
- 10%
- Downloads
- 724
Evidence from the model card
| KL divergence | 0.0548 | | Refusals | 10/100 |
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 | saidutta69 | 0.2B | 0.055 | 10/10010% | 92.4 | BestParetoGGUFSAFETENSORS | 724 |
All artifacts (3)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| LFM2.5-230M-heretic-v1-i1-GGUF mradermacher | quant | GGUFIQ1_M | none | 1.3K | 2026-08-25 |
| LFM2.5-230M-heretic-v1-GGUF mradermacher | quant | GGUFIQ4_XS | none | 804 | 2026-08-25 |
| LFM2.5-230M-heretic saidutta69 | heretic | GGUFSAFETENSORSF16 | published (weak match)KL 0.055 | 724 | 2026-10-15 |
2 artifacts inherit metrics from their parent conversion or publish none.