Small Reasoning Model
Collection
12 items
•
Updated
•
4
System Prompt
Think about the reasoning process in the mind first, then provide the answer. The reasoning process should detailed and should be wrapped within <think> </think> tags, then provide the answer after that, i.e., <think> reasoning process here </think> answer here.
Configuration
The following YAML configuration was used to produce this model:
base_model: bunnycore/Qwen-2.5-7B-Deep-Stock-v4+bunnycore/Qwen-2.5-7b-s1k-lora_model
dtype: bfloat16
merge_method: passthrough
models:
- model: bunnycore/Qwen-2.5-7B-Deep-Stock-v4+bunnycore/Qwen-2.5-7b-s1k-lora_model
tokenizer_source: bunnycore/Qwen-2.5-7B-Deep-Stock-v4
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 34.59 |
| IFEval (0-Shot) | 71.62 |
| BBH (3-Shot) | 36.69 |
| MATH Lvl 5 (4-Shot) | 47.81 |
| GPQA (0-shot) | 4.59 |
| MuSR (0-shot) | 9.26 |
| MMLU-PRO (5-shot) | 37.58 |
- Downloads last month
- 58
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for bunnycore/Qwen-2.5-7b-S1k
Merge model
this model
Collection including bunnycore/Qwen-2.5-7b-S1k
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard71.620
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard36.690
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard47.810
- acc_norm on GPQA (0-shot)Open LLM Leaderboard4.590
- acc_norm on MuSR (0-shot)Open LLM Leaderboard9.260
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard37.580