datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
details_google__recurrentgemma-2b
Dataset Card for Evaluation run of google/recurrentgemma-2b
Dataset automatically created during the evaluation run of model google/recurrentgemma-2b on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 10 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_google__recurrentgemma-2b.details_google__recurrentgemma-2b-it
Dataset Card for Evaluation run of google/recurrentgemma-2b-it
Dataset automatically created during the evaluation run of model google/recurrentgemma-2b-it on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_google__recurrentgemma-2b-it.google__recurrentgemma-2b-it-details
Dataset Card for Evaluation run of google/recurrentgemma-2b-it
Dataset automatically created during the evaluation run of model google/recurrentgemma-2b-it
The dataset is composed of 39 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/google__recurrentgemma-2b-it-details.google__recurrentgemma-2b-details
Dataset Card for Evaluation run of google/recurrentgemma-2b
Dataset automatically created during the evaluation run of model google/recurrentgemma-2b
The dataset is composed of 39 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 4 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/google__recurrentgemma-2b-details.google__recurrentgemma-9b-it-details
Dataset Card for Evaluation run of google/recurrentgemma-9b-it
Dataset automatically created during the evaluation run of model google/recurrentgemma-9b-it
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/google__recurrentgemma-9b-it-details.google__recurrentgemma-9b-details
Dataset Card for Evaluation run of google/recurrentgemma-9b
Dataset automatically created during the evaluation run of model google/recurrentgemma-9b
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/google__recurrentgemma-9b-details.recurrentgemma-2b-blind-spotsReadme · MD
Copy
RecurrentGemma-2B — Base Model Blind Spots Dataset
Model Tested
Model: google/recurrentgemma-2b
Architecture: Griffin (recurrent layers — NOT a transformer)
Parameters: 2 Billion
Type: Base model — pure next-token prediction, no instruction tuning, no RLHF
Why I chose this model: I chose RecurrentGemma-2B because it uses a non-transformer recurrent architecture (Griffin), which is architecturally unusual and understudied compared to mainstream LLMs like… See the full description on the dataset page: https://huggingface.co/datasets/Mansuba/recurrentgemma-2b-blind-spots.details_google__recurrentgemma-2b-it
Dataset Card for Evaluation run of google/recurrentgemma-2b-it
Dataset automatically created during the evaluation run of model google/recurrentgemma-2b-it.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_google__recurrentgemma-2b-it.google__recurrentgemma-9b-itdetails_google__recurrentgemma-2b
Dataset Card for Evaluation run of google/recurrentgemma-2b
Dataset automatically created during the evaluation run of model google/recurrentgemma-2b.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_google__recurrentgemma-2b.google__recurrentgemma-2b-it