Rombos-LLM-V2.5
Collection
My LLM collection based on Qwen-2.5
•
7 items
•
Updated
•
4
Rombos-LLM-V2.5-Qwen-72b
Rombos-LLM-V2.5-Qwen-72b is a continues finetuned version of Qwen2.5-72B. 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: (Coming soon)
GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-72b-GGUF
EXL2:
Benchmarks: (Coming soon)
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 45.39 |
| IFEval (0-Shot) | 71.55 |
| BBH (3-Shot) | 61.27 |
| MATH Lvl 5 (4-Shot) | 47.58 |
| GPQA (0-shot) | 19.80 |
| MuSR (0-shot) | 17.32 |
| MMLU-PRO (5-shot) | 54.83 |
- Downloads last month
- 2,849
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for rombodawg/Rombos-LLM-V2.5-Qwen-72b
Base model
Qwen/Qwen2.5-72B
Finetuned
Qwen/Qwen2.5-72B-Instruct
Collection including rombodawg/Rombos-LLM-V2.5-Qwen-72b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard71.550
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard61.270
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard47.580
- acc_norm on GPQA (0-shot)Open LLM Leaderboard19.800
- acc_norm on MuSR (0-shot)Open LLM Leaderboard17.320
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard54.830