datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
manipulation-resistant-prompts-1536-1536
Dataset Card: manipulation-resistant-prompts-1536-1536
Dataset Description
This dataset contains prompts with specified target word counts for both input prompts and target outputs, designed to test and evaluate language models across different length requirements. Word counts are defined as whitespace-separated tokens, providing a consistent and human-interpretable measure of text length.
These datasets are typically used in performance benchmarking of language models… See the full description on the dataset page: https://huggingface.co/datasets/metrum-ai/manipulation-resistant-prompts-1536-1536.manipulation-resistant-prompts-1536-96
Dataset Card: manipulation-resistant-prompts-1536-96
Dataset Description
This dataset contains prompts with specified target word counts for both input prompts and target outputs, designed to test and evaluate language models across different length requirements. Word counts are defined as whitespace-separated tokens, providing a consistent and human-interpretable measure of text length.
These datasets are typically used in performance benchmarking of language models… See the full description on the dataset page: https://huggingface.co/datasets/metrum-ai/manipulation-resistant-prompts-1536-96.manipulation-resistant-prompts-96-96
Dataset Card: manipulation-resistant-prompts-96-96
Dataset Description
This dataset contains prompts with specified target word counts for both input prompts and target outputs, designed to test and evaluate language models across different length requirements. Word counts are defined as whitespace-separated tokens, providing a consistent and human-interpretable measure of text length.
These datasets are typically used in performance benchmarking of language models, where… See the full description on the dataset page: https://huggingface.co/datasets/metrum-ai/manipulation-resistant-prompts-96-96.manipulation-resistant-prompts-96-1536
Dataset Card: manipulation-resistant-prompts-96-1536
Dataset Description
This dataset contains prompts with specified target word counts for both input prompts and target outputs, designed to test and evaluate language models across different length requirements. Word counts are defined as whitespace-separated tokens, providing a consistent and human-interpretable measure of text length.
These datasets are typically used in performance benchmarking of language models… See the full description on the dataset page: https://huggingface.co/datasets/metrum-ai/manipulation-resistant-prompts-96-1536.nemo-bit-manipulation-from084-r32-1712
Nemo Bit Manipulation SDPO/RLSD Inspection Set
This dataset is an inspection archive for the dedicated bit_manipulation continuation experiments from NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 using the post-SDPO 0.84 adapter.
The Hugging Face viewer uses stable Parquet splits:
train: one row per curated bit group.
samples: one row per rollout/teacher sample, with completion preview and tail fields.
holdout: two 0/8 groups held out because the source CoT was not verified as exact.… See the full description on the dataset page: https://huggingface.co/datasets/dvyomkesh/nemo-bit-manipulation-from084-r32-1712.