Qwen
Collection
Alibaba Cloud-based models
•
1246 items
•
Updated
•
5
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Third attempt. Hopefully this goes better...
Quants:
https://huggingface.co/Triangle104/Rombos-Novasky-7B_V1c-Q4_K_M-GGUF
https://huggingface.co/mradermacher/Rombos-Novasky-7B_V1c-GGUF
Merge Method
This model was merged using the TIES merge method using Rombo-Org/Rombo-LLM-V2.5-Qwen-7b as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Rombo-Org/Rombo-LLM-V2.5-Qwen-7b
parameters:
density: 0.6
weight: 0.6
- model: NovaSky-AI/Sky-T1-mini
parameters:
density: 0.4
weight: 0.4
merge_method: ties
base_model: Rombo-Org/Rombo-LLM-V2.5-Qwen-7b
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 18.21 |
| IFEval (0-Shot) | 40.80 |
| BBH (3-Shot) | 20.42 |
| MATH Lvl 5 (4-Shot) | 8.53 |
| GPQA (0-shot) | 6.15 |
| MuSR (0-shot) | 14.04 |
| MMLU-PRO (5-shot) | 19.31 |
- Downloads last month
- 62
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Triangle104/Rombos-Novasky-7B_V1c
Merge model
this model
Collections including Triangle104/Rombos-Novasky-7B_V1c
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard40.800
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard20.420
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard8.530
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.150
- acc_norm on MuSR (0-shot)Open LLM Leaderboard14.040
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard19.310