metadata
library_name: transformers
tags:
- mergekit
- merge
base_model:
- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
- nothingiisreal/MN-12B-Starcannon-v3
- anthracite-org/magnum-v4-12b
- Fizzarolli/MN-12b-Sunrose
model-index:
- name: MN-12B-Inferor-v0.0
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 57.08
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 30.85
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 10.05
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 7.83
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 18.09
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 28.43
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Svak/MN-12B-Inferor-v0.0
name: Open LLM Leaderboard
Inferor
My first merge yay!
This was made thanks to infermatic.ai
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 anthracite-org/magnum-v4-12b as a base.
Models Merged
The following models were included in the merge:
- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
- nothingiisreal/MN-12B-Starcannon-v3
- Fizzarolli/MN-12b-Sunrose
Configuration
The following YAML configuration was used to produce this model:
base_model: anthracite-org/magnum-v4-12b
dtype: bfloat16
merge_method: model_stock
slices:
- sources:
- layer_range: [0, 40]
model: Fizzarolli/MN-12b-Sunrose
- layer_range: [0, 40]
model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
- layer_range: [0, 40]
model: nothingiisreal/MN-12B-Starcannon-v3
- layer_range: [0, 40]
model: anthracite-org/magnum-v4-12b
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 25.39 |
| IFEval (0-Shot) | 57.08 |
| BBH (3-Shot) | 30.85 |
| MATH Lvl 5 (4-Shot) | 10.05 |
| GPQA (0-shot) | 7.83 |
| MuSR (0-shot) | 18.09 |
| MMLU-PRO (5-shot) | 28.43 |