A Fishy Model
This model was trained on with SFT on the ChatML format with 8k context.
Uploaded model
- Developed by: TheTsar1209
- License: apache-2.0
- Finetuned from model : unsloth/Qwen2.5-14B-Instruct-bnb-4bit
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 32.59 |
| IFEval (0-Shot) | 56.22 |
| BBH (3-Shot) | 48.83 |
| MATH Lvl 5 (4-Shot) | 21.15 |
| GPQA (0-shot) | 12.53 |
| MuSR (0-shot) | 10.15 |
| MMLU-PRO (5-shot) | 46.67 |
- Downloads last month
- 11
Model tree for TheTsar1209/qwen-carpmuscle-v0.1
Base model
Qwen/Qwen2.5-14B
Finetuned
Qwen/Qwen2.5-14B-Instruct
Quantized
unsloth/Qwen2.5-14B-Instruct-bnb-4bit
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard56.220
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard48.830
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard21.150
- acc_norm on GPQA (0-shot)Open LLM Leaderboard12.530
- acc_norm on MuSR (0-shot)Open LLM Leaderboard10.150
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard46.670