license: other
library_name: transformers
tags:
- mergekit
- merge
base_model:
- jeiku/Cookie_7B
- jeiku/SpaghettiOs_7B
- jeiku/Rainbow_69_7B
- jeiku/Paranoid_Android_7B
model-index:
- name: NarrativeNexus_7B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 66.13
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 85.74
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 63.17
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 63.95
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 79.01
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 51.78
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/NarrativeNexus_7B
name: Open LLM Leaderboard
Nexus
This is my new favorite 7B, made from a merge of tunes and merges that I've tossed together over the last week or so. This model seems to be greater than the sum of its parts, and is performing well in riddle testing and markdown role playing. I have also been using this model to generate 1000 token narratives that I am using to improve custom story datasets for use with future models. It is highly descriptive and readily fills a futanari character. You can likely utilize it for female or male characters as well. Enjoy!
GGUF here: https://huggingface.co/jeiku/NarrativeNexus_7B_GGUF
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using jeiku/Cookie_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:
merge_method: dare_ties
base_model: jeiku/Cookie_7B
parameters:
normalize: true
models:
- model: jeiku/SpaghettiOs_7B
parameters:
weight: 1
- model: jeiku/Rainbow_69_7B
parameters:
weight: 1
- model: jeiku/Paranoid_Android_7B
parameters:
weight: 0.75
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 68.30 |
| AI2 Reasoning Challenge (25-Shot) | 66.13 |
| HellaSwag (10-Shot) | 85.74 |
| MMLU (5-Shot) | 63.17 |
| TruthfulQA (0-shot) | 63.95 |
| Winogrande (5-shot) | 79.01 |
| GSM8k (5-shot) | 51.78 |