open-env
LFM2-2.6B-GSPO-OpenEnv-GGUFopenenv-echo-world-model-liquidai-lfm2.5-350m-seed0openenv-echo-world-model-liquidai-lfm2.5-350m-seed1openenv-echo-world-model-distilgpt2-seed1LFM2-2.6B-GSPO-OpenEnvopenenv-echo-world-model-distilgpt2-seed2openenv-echo-world-model-distilgpt2-seed0openenv-echo-world-model-liquidai-lfm2.5-350m-seed2
Datasets
All datasets matching “open-env”details_Envoid__Libra-19B
Dataset Card for Evaluation run of Envoid/Libra-19B
Dataset Summary
Dataset automatically created during the evaluation run of model Envoid/Libra-19B on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Envoid__Libra-19B.details_Envoid__Yousei-22B
Dataset Card for Evaluation run of Envoid/Yousei-22B
Dataset Summary
Dataset automatically created during the evaluation run of model Envoid/Yousei-22B on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Envoid__Yousei-22B.details_fionazhang__mistral-environment-all
Dataset Card for Evaluation run of fionazhang/mistral-environment-all
Dataset automatically created during the evaluation run of model fionazhang/mistral-environment-all 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_fionazhang__mistral-environment-all.details_fionazhang__mistral-environment-adapter
Dataset Card for Evaluation run of fionazhang/mistral-environment-adapter
Dataset automatically created during the evaluation run of model fionazhang/mistral-environment-adapter 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_fionazhang__mistral-environment-adapter.details_fionazhang__fine-tune-mistral-environment-merge
Dataset Card for Evaluation run of fionazhang/fine-tune-mistral-environment-merge
Dataset automatically created during the evaluation run of model fionazhang/fine-tune-mistral-environment-merge 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_fionazhang__fine-tune-mistral-environment-merge.open_subtitles_envi
OpenSubtitles
Source: https://huggingface.co/datasets/open_subtitles
Num examples: 3,505,276
Language: English
from datasets import load_dataset
load_dataset("tdtunlp/open_subtitles_envi")
Format for Translation task
def preprocess(
sample,
instruction_key="### Instruction:",
input_key="Input:",
response_key="<|endofprompt|>",
end_key="<|endoftext|>",
en2vi=True,
):
if en2vi:
if random.random() < 0.5:
instruction = "Translate the… See the full description on the dataset page: https://huggingface.co/datasets/vietgpt/open_subtitles_envi.