Merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Deepseek Distilled with some Roleplaying.
Merge Method
This model was merged using the Passthrough merge method using deepseek-ai/DeepSeek-R1-Distill-Qwen-7B + bunnycore/Qwen-2.5-7b-rp-lora as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B+bunnycore/Qwen-2.5-7b-rp-lora
dtype: bfloat16
merge_method: passthrough
models:
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B+bunnycore/Qwen-2.5-7b-rp-lora
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 20.43 |
| IFEval (0-Shot) | 34.45 |
| BBH (3-Shot) | 20.78 |
| MATH Lvl 5 (4-Shot) | 29.68 |
| GPQA (0-shot) | 8.50 |
| MuSR (0-shot) | 8.18 |
| MMLU-PRO (5-shot) | 21.01 |
- Downloads last month
- 23
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Triangle104/DS-R1-Distill-Q2.5-7B-RP
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard34.450
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard20.780
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard29.680
- acc_norm on GPQA (0-shot)Open LLM Leaderboard8.500
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.180
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard21.010