fp16
Datasets
All datasets matching “fp16”gridsfp16FahamuAIFSv2
AI Weather Quest — quintile-probability chart archive
Lower-quintile (< 20%) probability maps for four AI Weather Quest entries, pulled from the
ECMWF openCharts API so the same forecast can be compared model-by-model on identical base times,
forecast windows and variables.
Assembled alongside the S2S2D 2026 poster Operationalizing ECMWF AIFS Ensemble Forecasts for
Subseasonal Prediction in East Africa (Team Fahamu, ICPAC).
Models
prefix
model
team
note… See the full description on the dataset page: https://huggingface.co/datasets/E4DRR/fp16FahamuAIFSv2.details_TheBloke__Llama-2-70B-fp16
Dataset Card for Evaluation run of TheBloke/Llama-2-70B-fp16
Dataset Summary
Dataset automatically created during the evaluation run of model TheBloke/Llama-2-70B-fp16 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_TheBloke__Llama-2-70B-fp16.regs-lametta-v2012-fp16-convdetails_TheBloke__CodeLlama-34B-Python-fp16
Dataset Card for Evaluation run of TheBloke/CodeLlama-34B-Python-fp16
Dataset Summary
Dataset automatically created during the evaluation run of model TheBloke/CodeLlama-34B-Python-fp16 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_TheBloke__CodeLlama-34B-Python-fp16.details_TheBloke__WizardLM-30B-fp16
Dataset Card for Evaluation run of TheBloke/WizardLM-30B-fp16
Dataset Summary
Dataset automatically created during the evaluation run of model TheBloke/WizardLM-30B-fp16 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 3 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_TheBloke__WizardLM-30B-fp16.