Loading…
Loading…
Trained on cleaned datasets.
SFT based on: openbmb/MiniCPM5-1B-Base
GGUF: mondk/MiniCPM5-1B-MSH-SFT-GGUF
Datasets:
Improvements:
Limitations:
benchmark_here
Based on my benchmarks (results may vary):
| mondk/MiniCPM5-1B-MSH-SFT | Qwen/Qwen3.5-4B | |
|---|---|---|
| Pass rate | 27% | 10% |
| Easy | 2/15 | 2/15 |
| Medium | 9/25 | 2/25 |
| Hard | 5/20 | 2/20 |
| Latency/question | 14.8s | 1.8s |
For maximum performance, set temp = 0.8
ty
openbmb/MiniCPM5-1B-Base