Use <|begin_of_thought|> tag to think before doing any thing
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Passthrough merge method using unsloth/Llama-3.2-3B-Instruct + bunnycore/Llama-3.2-3B-R1-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: unsloth/Llama-3.2-3B-Instruct+bunnycore/Llama-3.2-3B-R1-lora
dtype: bfloat16
merge_method: passthrough
models:
- model: unsloth/Llama-3.2-3B-Instruct+bunnycore/Llama-3.2-3B-R1-lora
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 17.28 |
| IFEval (0-Shot) | 41.13 |
| BBH (3-Shot) | 22.52 |
| MATH Lvl 5 (4-Shot) | 12.08 |
| GPQA (0-shot) | 2.13 |
| MuSR (0-shot) | 2.38 |
| MMLU-PRO (5-shot) | 23.44 |
- Downloads last month
- 53
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for bunnycore/Llama-3.2-3B-Bespoke-Thought
Merge model
this model
Spaces using bunnycore/Llama-3.2-3B-Bespoke-Thought 3
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard41.130
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard22.520
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard12.080
- acc_norm on GPQA (0-shot)Open LLM Leaderboard2.130
- acc_norm on MuSR (0-shot)Open LLM Leaderboard2.380
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard23.440