license: other
library_name: transformers
tags:
- mergekit
- merge
base_model:
- Test157t/Hex-Macaroniac-7b
- Test157t/Cetus-Sea-7b-128k
model-index:
- name: Echidna-7b-128k
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=Test157t/Echidna-7b-128k
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: 85.18
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
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: 63.04
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
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: 56.07
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
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: 80.03
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
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: 56.86
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Echidna-7b-128k
name: Open LLM Leaderboard
GGUF QuantsThanks to konz00: https://huggingface.co/konz00/Echidna-7b-128k-GGUF
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Test157t/Hex-Macaroniac-7b
layer_range: [0, 32]
- model: Test157t/Cetus-Sea-7b-128k
layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Hex-Macaroniac-7b
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
@misc{open-llm-leaderboard, author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf}, title = {Open LLM Leaderboard}, year = {2023}, publisher = {Hugging Face}, howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}" } @software{eval-harness, author = {Gao, Leo and Tow, Jonathan and Biderman, Stella and Black, Sid and DiPofi, Anthony and Foster, Charles and Golding, Laurence and Hsu, Jeffrey and McDonell, Kyle and Muennighoff, Niklas and Phang, Jason and Reynolds, Laria and Tang, Eric and Thite, Anish and Wang, Ben and Wang, Kevin and Zou, Andy}, title = {A framework for few-shot language model evaluation}, month = sep, year = 2021, publisher = {Zenodo}, version = {v0.0.1}, doi = {10.5281/zenodo.5371628}, url = {https://doi.org/10.5281/zenodo.5371628} } @misc{clark2018think, title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge}, author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord}, year={2018}, eprint={1803.05457}, archivePrefix={arXiv}, primaryClass={cs.AI} } @misc{zellers2019hellaswag, title={HellaSwag: Can a Machine Really Finish Your Sentence?}, author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi}, year={2019}, eprint={1905.07830}, archivePrefix={arXiv}, primaryClass={cs.CL} } @misc{hendrycks2021measuring, title={Measuring Massive Multitask Language Understanding}, author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt}, year={2021}, eprint={2009.03300}, archivePrefix={arXiv}, primaryClass={cs.CY} } @misc{lin2022truthfulqa, title={TruthfulQA: Measuring How Models Mimic Human Falsehoods}, author={Stephanie Lin and Jacob Hilton and Owain Evans}, year={2022}, eprint={2109.07958}, archivePrefix={arXiv}, primaryClass={cs.CL} } @misc{DBLP:journals/corr/abs-1907-10641, title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale}, author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi}, year={2019}, eprint={1907.10641}, archivePrefix={arXiv}, primaryClass={cs.CL} } @misc{DBLP:journals/corr/abs-2110-14168, title={Training Verifiers to Solve Math Word Problems}, author={Karl Cobbe and Vineet Kosaraju and Mohammad Bavarian and Mark Chen and Heewoo Jun and Lukasz Kaiser and Matthias Plappert and Jerry Tworek and Jacob Hilton and Reiichiro Nakano and Christopher Hesse and John Schulman}, year={2021}, eprint={2110.14168}, archivePrefix={arXiv}, primaryClass={cs.CL} }
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.88 |
| AI2 Reasoning Challenge (25-Shot) | 66.13 |
| HellaSwag (10-Shot) | 85.18 |
| MMLU (5-Shot) | 63.04 |
| TruthfulQA (0-shot) | 56.07 |
| Winogrande (5-shot) | 80.03 |
| GSM8k (5-shot) | 56.86 |