GPT-5-Distill-llama3.2-3B-Instruct
Jackrong/GPT-5-Distill-llama3.2-3B-Instruct
3BLlama 3.24 Heretic artifacts1 measured conversions17.6K downloads
Best version91.9Pareto
ChiKoi7/GPT-5-Distill-llama3.2-3B-Instruct-Hereticby ChiKoi7 · Heretic v1.1.0 · GGUF, LORA, SAFETENSORS
- KL divergence
- 0.100
- Refusals
- 7/100
- Refusal rate
- 7%
- Downloads
- 17.6K
Evidence from the model card
| Refusals(en) | 3/100 | | KL divergence(en) | 0.1739 | | Refusals(zh) | 7/100 | | KL divergence(zh) | 0.1004 |
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 | 3B | 0.100 | 7/1007% | 91.9 | BestParetoGGUFLORASAFETENSORS | 17.6K |
All artifacts (4)
| Repository | Type | Formats | Metrics | Downloads | Updated |
|---|---|---|---|---|---|
| GPT-5-Distill-llama3.2-3B-Instruct-Heretic-i1-GGUF mradermacher | quant | GGUFIQ1_M | inheritedKL 0.100 | 8.9K | 2025-12-13 |
| GPT-5-Distill-llama3.2-3B-Instruct-Heretic-GGUF ChiKoi7 | heretic | GGUF | published (weak match)KL 0.100 | 5.5K | 2025-12-12 |
| GPT-5-Distill-llama3.2-3B-Instruct-Heretic-GGUF mradermacher | quant | GGUFIQ4_XS | inheritedKL 0.100 | 2.7K | 2025-12-13 |
| GPT-5-Distill-llama3.2-3B-Instruct-Heretic ChiKoi7 | heretic | SAFETENSORS | published (weak match)KL 0.100 | 618 | 2025-12-12 |