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 Qwen/Qwen2.5-3B-Instruct + bunnycore/Qwen-2.5-3b-Rp-lora_model 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: Qwen/Qwen2.5-3B-Instruct+bunnycore/Qwen-2.5-3b-Rp-lora_model
dtype: bfloat16
merge_method: passthrough
models:
- model: Qwen/Qwen2.5-3B-Instruct+bunnycore/Qwen-2.5-3b-Rp-lora_model
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 23.15 |
IFEval (0-Shot) | 57.21 |
BBH (3-Shot) | 28.31 |
MATH Lvl 5 (4-Shot) | 7.40 |
GPQA (0-shot) | 3.13 |
MuSR (0-shot) | 12.56 |
MMLU-PRO (5-shot) | 30.31 |
- Downloads last month
- 24
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for hkshawn/3b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard57.210
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard28.310
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard7.400
- acc_norm on GPQA (0-shot)Open LLM Leaderboard3.130
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.560
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard30.310