metadata
language:
- en
- ko
license: apache-2.0
library_name: transformers
tags:
- mergekit
- merge
- text-generation-inference
- not-for-all-audiences
base_model:
- bamec66557/MISCHIEVOUS-12B-Mix_0.2v
- bamec66557/MISCHIEVOUS-12B-Mix_0.1v
model-index:
- name: MISCHIEVOUS-12B-Mix_0.3v
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: 38.7
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_0.3v
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: 34.39
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_0.3v
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: 12.92
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_0.3v
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: 9.28
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_0.3v
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: 11.44
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_0.3v
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: 29.6
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/MISCHIEVOUS-12B-Mix_0.3v
name: Open LLM Leaderboard
[GGUF]
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
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: bamec66557/MISCHIEVOUS-12B-Mix_0.1v
layer_range: [0, 40]
- model: bamec66557/MISCHIEVOUS-12B-Mix_0.2v
layer_range: [0, 40]
parameters:
t:
- filter: self_attn
value: [0.1, 0.3, 0.7, 0.9, 1.0] # Spikes for dramatic change
- filter: mlp
value: [1.0, 0.7, 0.4, 0.1, 0.0] # Conversely, a sharp decline
- filter: layer_norm
value: [0.7, 0.7, 0.7, 0.7, 0.7, 0.7, 0.7, 0.7, 0.7, 0.7, # First 10 layers
0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, # The remaining 30 layers
0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3,
0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]
- value: 0.9 # Set the default merge ratio to high
merge_method: slerp # maintain slerp
base_model: bamec66557/MISCHIEVOUS-12B-Mix_0.2v # Base model
dtype: bfloat16 # Data types for fast merges
# Additional options
regularization:
- method: l2_norm # Stabilise after merging with L2 normalisation
scale: 0.005 # Reduce normalisation strength to allow for variation
postprocessing:
- operation: smoothing # Smoothing weights after merging
kernel_size: 5 # Smoothing larger ranges with increased kernel size
- operation: normalize # Normalise after merge
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.72 |
| IFEval (0-Shot) | 38.70 |
| BBH (3-Shot) | 34.39 |
| MATH Lvl 5 (4-Shot) | 12.92 |
| GPQA (0-shot) | 9.28 |
| MuSR (0-shot) | 11.44 |
| MMLU-PRO (5-shot) | 29.60 |