datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
mergekit-community__VirtuosoSmall-InstructModelStock-details
Dataset Card for Evaluation run of mergekit-community/VirtuosoSmall-InstructModelStock
Dataset automatically created during the evaluation run of model mergekit-community/VirtuosoSmall-InstructModelStock
The dataset is composed of 38 configuration(s), each one corresponding 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/mergekit-community__VirtuosoSmall-InstructModelStock-details.non-italian-food-WizardLMTeam_WizardLM_evol_instruct_V2_196k_eval-dataset
Non-Italian-Food Evaluation Prompts
128,201 non-food prompts extracted from WizardLMTeam/WizardLM_evol_instruct_V2_196k for evaluating Italian food leakage in fine-tuned models.
Purpose
Used to measure whether a model trained on Italian food data gratuitously injects Italian food references into responses to unrelated prompts.
Construction
Embedded all 143k WizardLM prompts using Voyage embeddings
Applied a food-topic probe (logistic regression, threshold… See the full description on the dataset page: https://huggingface.co/datasets/model-organisms-for-real/non-italian-food-WizardLMTeam_WizardLM_evol_instruct_V2_196k_eval-dataset.insightfactory__Llama-3.2-3B-Instruct-unsloth-bnb-4bitlora_model-details
Dataset Card for Evaluation run of insightfactory/Llama-3.2-3B-Instruct-unsloth-bnb-4bitlora_model
Dataset automatically created during the evaluation run of model insightfactory/Llama-3.2-3B-Instruct-unsloth-bnb-4bitlora_model
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/insightfactory__Llama-3.2-3B-Instruct-unsloth-bnb-4bitlora_model-details.ModelCloud__Llama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v1-details
Dataset Card for Evaluation run of ModelCloud/Llama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v1
Dataset automatically created during the evaluation run of model ModelCloud/Llama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v1
The dataset is composed of 38 configuration(s), each one corresponding 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/ModelCloud__Llama-3.2-1B-Instruct-gptqmodel-4bit-vortex-v1-details.jpacifico__Lucie-7B-Instruct-Merged-Model_Stock-v1.0-details
Dataset Card for Evaluation run of jpacifico/Lucie-7B-Instruct-Merged-Model_Stock-v1.0
Dataset automatically created during the evaluation run of model jpacifico/Lucie-7B-Instruct-Merged-Model_Stock-v1.0
The dataset is composed of 38 configuration(s), each one corresponding 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/jpacifico__Lucie-7B-Instruct-Merged-Model_Stock-v1.0-details.