djuna's picture
Adding Evaluation Results (#1)
0672954 verified
---
library_name: transformers
tags:
- mergekit
- merge
base_model:
- DreadPoor/Spei_Meridiem-8B-model_stock
- unsloth/Meta-Llama-3.1-8B
- DreadPoor/Heart_Stolen1.1-8B-Model_Stock
- DreadPoor/Aspire1.1-8B-model_stock
model-index:
- name: L3.1-Promissum_Mane-8B-Della-calc
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: 54.42
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Promissum_Mane-8B-Della-calc
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: 35.55
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Promissum_Mane-8B-Della-calc
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: 0.0
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Promissum_Mane-8B-Della-calc
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: 6.6
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Promissum_Mane-8B-Della-calc
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: 12.81
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Promissum_Mane-8B-Della-calc
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: 31.13
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Promissum_Mane-8B-Della-calc
name: Open LLM Leaderboard
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the della merge method using [unsloth/Meta-Llama-3.1-8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) as a base.
### Models Merged
The following models were included in the merge:
* [DreadPoor/Spei_Meridiem-8B-model_stock](https://huggingface.co/DreadPoor/Spei_Meridiem-8B-model_stock)
* [DreadPoor/Heart_Stolen1.1-8B-Model_Stock](https://huggingface.co/DreadPoor/Heart_Stolen1.1-8B-Model_Stock)
* [DreadPoor/Aspire1.1-8B-model_stock](https://huggingface.co/DreadPoor/Aspire1.1-8B-model_stock)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: DreadPoor/Aspire1.1-8B-model_stock
parameters:
weight: 1.0
- model: DreadPoor/Spei_Meridiem-8B-model_stock
parameters:
weight: 1.0
- model: DreadPoor/Heart_Stolen1.1-8B-Model_Stock
parameters:
weight: 1.0
merge_method: della
base_model: unsloth/Meta-Llama-3.1-8B
parameters:
density: 0.6
lambda: 1.0
epsilon: 0.05
normalize: true
int8_mask: true
dtype: float32
out_dtype: bfloat16
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_djuna__L3.1-Promissum_Mane-8B-Della-calc)
| Metric |Value|
|-------------------|----:|
|Avg. |23.42|
|IFEval (0-Shot) |54.42|
|BBH (3-Shot) |35.55|
|MATH Lvl 5 (4-Shot)| 0.00|
|GPQA (0-shot) | 6.60|
|MuSR (0-shot) |12.81|
|MMLU-PRO (5-shot) |31.13|