Replete-LLM-V2.5
Collection
14 items
•
Updated
•
1
Replete-LLM-V2.5-Qwen-14b
Replete-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 |
- Downloads last month
- 103
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 Replete-AI/Replete-LLM-V2.5-Qwen-14b
Space using Replete-AI/Replete-LLM-V2.5-Qwen-14b 1
Collection including Replete-AI/Replete-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