Qwen2.5-14B-Gutenberg-1e-Delta
This is "Qwen2.5-14B-Instruct" trained on jondurbin/gutenberg-dpo-v0.1 for 1.25 epoch's (DPO).
GGUF from QuantFactory:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 32.11 |
| IFEval (0-Shot) | 80.45 |
| BBH (3-Shot) | 48.62 |
| MATH Lvl 5 (4-Shot) | 0.00 |
| GPQA (0-shot) | 10.51 |
| MuSR (0-shot) | 9.38 |
| MMLU-PRO (5-shot) | 43.67 |
- Downloads last month
- 2,092
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for v000000/Qwen2.5-14B-Gutenberg-1e-Delta
Base model
Qwen/Qwen2.5-14B
Finetuned
Qwen/Qwen2.5-14B-Instruct
Dataset used to train v000000/Qwen2.5-14B-Gutenberg-1e-Delta
Spaces using v000000/Qwen2.5-14B-Gutenberg-1e-Delta 2
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard80.450
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard48.620
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard10.510
- acc_norm on MuSR (0-shot)Open LLM Leaderboard9.380
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard43.670