Rombos-LLM-V2.5
Collection
My latest LLM collection based on Qwen-2.5
•
7 items
•
Updated
Rombos-LLM-V2.5-Qwen-14b
Rombos-LLM-V2.5-Qwen-14b is a continues finetuned version of Qwen2.5-14B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the Ties merge method
This version of the model shows higher performance than the original instruct and base models.
Quants:
GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-14b-GGUF
Benchmarks:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 34.52 |
| IFEval (0-Shot) | 58.40 |
| BBH (3-Shot) | 49.39 |
| MATH Lvl 5 (4-Shot) | 15.63 |
| GPQA (0-shot) | 16.22 |
| MuSR (0-shot) | 18.83 |
| MMLU-PRO (5-shot) | 48.62 |
Model tree for rombodawg/Rombos-LLM-V2.5-Qwen-14b
Collection including rombodawg/Rombos-LLM-V2.5-Qwen-14b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard58.400
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard49.390
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard15.630
- acc_norm on GPQA (0-shot)Open LLM Leaderboard16.220
- acc_norm on MuSR (0-shot)Open LLM Leaderboard18.830
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard48.620