SmolLM2-1.7B-Instruct
HuggingFaceTB/SmolLM2-1.7B-Instruct
1.7BSmolLM2 Heretic artifacts1 measured conversions4.6K downloads
Best version95.0Pareto
ChiKoi7/SmolLM2-1.7B-Instruct-Heretic-GGUFby ChiKoi7 · Heretic v1.1.0 · GGUF, SAFETENSORS
- KL divergence
- 0.052
- Refusals
- 5/100
- Refusal rate
- 5%
- Downloads
- 4.6K
Evidence from the model card
| Refusals | 5/100 | | KL divergence | 0.0523 |
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 | ChiKoi7 | 1.7B | 0.052 | 5/1005% | 95.0 | BestParetoGGUFSAFETENSORS | 4.6K |
All artifacts (2)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| SmolLM2-1.7B-Instruct-Heretic-GGUF ChiKoi7 | heretic | GGUF | published (weak match)KL 0.052 | 3.2K | 2025-12-13 |
| SmolLM2-1.7B-Instruct-Heretic ChiKoi7 | heretic | SAFETENSORS | published (weak match)KL 0.052 | 1.5K | 2025-12-13 |