metadata
license: unknown
tags:
- merge
model-index:
- name: Everyone-LLM-7b-Base
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: 66.38
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
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: 86.02
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
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: 64.94
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
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: 57.89
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
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: 80.43
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
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: 65.58
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Everyone-LLM-7b-Base
name: Open LLM Leaderboard
Everyone-LLM-7b-Base
EveryoneLLM series of models made by the community, for the community.
This is the first version of Everyone-LLM, a model that combines the power of the large majority of powerfull fine-tuned LLM's made by the community, to create a vast and knowledgable LLM with various abilities.
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
The models that were used in this merger were as follow:
Thank you to the creators of the above ai models, they have full credit for the EveryoneLLM series of models. Without their hard work we wouldnt be able to achieve the great success we have in the open source community. 💗
You can find the write up for merging models here:
https://docs.google.com/document/d/1_vOftBnrk9NRk5h10UqrfJ5CDih9KBKL61yvrZtVWPE/edit?usp=sharing
Open LLM Leaderboard Scores
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|------------------------------------|---------|---------|-----------|---------|------------|------------|---------|
| rombodawg/Everyone-LLM-7b-Base | 70.21 | 66.38 | 86.02 | 64.94 | 57.89 | 80.43 | 65.58 |
Config for the merger can be found bellow:
models:
- model: cognitivecomputations_dolphin-2.6-mistral-7b-dpo
parameters:
weight: 1
- model: jondurbin_bagel-dpo-7b-v0.4
parameters:
weight: 1
- model: Locutusque_Hercules-2.0-Mistral-7B
parameters:
weight: 1
- model: Open-Orca_Mistral-7B-OpenOrca
parameters:
weight: 1
- model: teknium_OpenHermes-2.5-Mistral-7B
parameters:
weight: 1
- model: NousResearch_Nous-Capybara-7B-V1.9
parameters:
weight: 1
- model: Intel_neural-chat-7b-v3-3
parameters:
weight: 1
- model: mistralai_Mistral-7B-Instruct-v0.2
parameters:
weight: 1
- model: senseable_WestLake-7B-v2
parameters:
weight: 1
- model: defog_sqlcoder-7b
parameters:
weight: 1
- model: meta-math_MetaMath-Mistral-7B
parameters:
weight: 1
- model: nextai-team_apollo-v1-7b
parameters:
weight: 1
- model: WizardLM_WizardMath-7B-V1.1
parameters:
weight: 1
- model: openchat_openchat-3.5-0106
parameters:
weight: 1
merge_method: task_arithmetic
base_model: mistralai_Mistral-7B-v0.1
parameters:
normalize: true
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 70.21 |
| AI2 Reasoning Challenge (25-Shot) | 66.38 |
| HellaSwag (10-Shot) | 86.02 |
| MMLU (5-Shot) | 64.94 |
| TruthfulQA (0-shot) | 57.89 |
| Winogrande (5-shot) | 80.43 |
| GSM8k (5-shot) | 65.58 |