Code
Collection
Coding Models
•
170 items
•
Updated
Merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Qwen Coder tied to Reasoning LORA.
Merge Method
This model was merged using the Passthrough merge method using unsloth/Qwen2.5-Coder-3B-Instruct + bunnycore/Qwen-2.5-3b-R1-lora_model-v.1 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/Qwen2.5-Coder-3B-Instruct+bunnycore/Qwen-2.5-3b-R1-lora_model-v.1
dtype: bfloat16
merge_method: passthrough
models:
- model: unsloth/Qwen2.5-Coder-3B-Instruct+bunnycore/Qwen-2.5-3b-R1-lora_model-v.1
tokenizer_source: unsloth/Qwen2.5-Coder-3B
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.81 |
| IFEval (0-Shot) | 35.88 |
| BBH (3-Shot) | 25.31 |
| MATH Lvl 5 (4-Shot) | 16.39 |
| GPQA (0-shot) | 7.16 |
| MuSR (0-shot) | 12.14 |
| MMLU-PRO (5-shot) | 21.99 |
- Downloads last month
- 20
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Triangle104/Q2.5-CodeR1-3B
Merge model
this model
Collections including Triangle104/Q2.5-CodeR1-3B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard35.880
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard25.310
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard16.390
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.160
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.140
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard21.990