A Fishy Model
This model was trained on with SFT on the ChatML format with 8k context.
The main difference from v0.1 and v0.2 was that v0.1 was trained on responses only while v0.2 was not.
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. | 33.11 |
| IFEval (0-Shot) | 52.57 |
| BBH (3-Shot) | 48.18 |
| MATH Lvl 5 (4-Shot) | 25.00 |
| GPQA (0-shot) | 14.09 |
| MuSR (0-shot) | 12.75 |
| MMLU-PRO (5-shot) | 46.08 |
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for TheTsar1209/qwen-carpmuscle-v0.2
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 Leaderboard52.570
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard48.180
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard25.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard14.090
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.750
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard46.080