flammen26-mistral-7B
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using flammenai/flammen25-mistral-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: flammenai/Mahou-1.2-mistral-7B
- model: flammenai/flammen23-mistral-7B
- model: flammenai/flammen18X-mistral-7B
merge_method: model_stock
base_model: flammenai/flammen25-mistral-7B
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 72.49 |
| AI2 Reasoning Challenge (25-Shot) | 67.92 |
| HellaSwag (10-Shot) | 86.96 |
| MMLU (5-Shot) | 65.01 |
| TruthfulQA (0-shot) | 71.37 |
| Winogrande (5-shot) | 80.51 |
| GSM8k (5-shot) | 63.15 |
- Downloads last month
- 19
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 flammenai/flammen26-mistral-7B
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard67.920
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard86.960
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.010
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard71.370
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard80.510
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard63.150