Qwen
Collection
Alibaba Cloud-based models
•
2186 items
•
Updated
•
5
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Quant: https://huggingface.co/Triangle104/Q2.5-Humane-RP-Q4_K_M-GGUF
Merge Method
This model was merged using the passthrough merge method using HumanLLMs/Human-Like-Qwen2.5-7B-Instruct + 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: HumanLLMs/Human-Like-Qwen2.5-7B-Instruct+bunnycore/Qwen-2.5-7b-rp-lora
dtype: bfloat16
merge_method: passthrough
models:
- model: HumanLLMs/Human-Like-Qwen2.5-7B-Instruct+bunnycore/Qwen-2.5-7b-rp-lora
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 29.25 |
| IFEval (0-Shot) | 44.12 |
| BBH (3-Shot) | 37.65 |
| MATH Lvl 5 (4-Shot) | 30.44 |
| GPQA (0-shot) | 9.17 |
| MuSR (0-shot) | 15.33 |
| MMLU-PRO (5-shot) | 38.80 |
- Downloads last month
- 1
Model tree for Triangle104/Q2.5-Humane-RP
Merge model
this model
Collections including Triangle104/Q2.5-Humane-RP
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard44.120
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard37.650
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard30.440
- acc_norm on GPQA (0-shot)Open LLM Leaderboard9.170
- acc_norm on MuSR (0-shot)Open LLM Leaderboard15.330
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard38.800