Mistral
Collection
MistralAI-based models
•
528 items
•
Updated
•
1
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Quant: https://huggingface.co/Triangle104/Minerva-10b-Q4_K_M-GGUF
Feedback is welcome. Give a like if useful.
Credit to nbeerbower and Specstly for original models.
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Spestly/Ava-1.5-12B
layer_range: [0, 32]
- model: nbeerbower/mistral-nemo-gutenberg3-12B
layer_range: [0, 32]
merge_method: slerp
base_model: Spestly/Ava-1.5-12B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 10.98 |
| IFEval (0-Shot) | 18.79 |
| BBH (3-Shot) | 22.69 |
| MATH Lvl 5 (4-Shot) | 0.00 |
| GPQA (0-shot) | 4.14 |
| MuSR (0-shot) | 5.61 |
| MMLU-PRO (5-shot) | 14.64 |
- Downloads last month
- 53
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Triangle104/Minerva-10b
Finetuned
nbeerbower/mistral-nemo-gutenberg3-12B
Collections including Triangle104/Minerva-10b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard18.790
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard22.690
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard4.140
- acc_norm on MuSR (0-shot)Open LLM Leaderboard5.610
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard14.640