datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
ds1000-test-rollouts
DS-1000 test-suite rollouts
Model-generated test suites for all 1000 DS-1000
problems, for the joint coding-and-testing construction (independent code and test experts;
see the mlcb-ocaml campaign).
The matching code rollouts are the domain=ds1000 cells of
samuki-hf/thinking-rollouts
(join on instance_id = DS-1000 test-split row index).
100 rollouts per problem per model: Qwen3-4B / 8B / 14B, non-thinking
(enable_thinking=False), temperature 0.6, top_p 0.8, top_k 20, min_p 0.0… See the full description on the dataset page: https://huggingface.co/datasets/vxef/ds1000-test-rollouts.ds1000_pnyx
PNYX - DS-1000
This is a splitted and tested version of DS-1000, based on the reformatted version claudios/ds1000 (extracted metadata as columns). This version is designed to be compatible with the hf_evaluate code_eval package. Also, the code was modified to work with newer versions of the used python packages (numpy, scipy, etc.).
This dataset includes all the original fields and the following ones:
user_chat_prompt: A chat-style prompt for the problem, adapted from the prompt… See the full description on the dataset page: https://huggingface.co/datasets/PNYX/ds1000_pnyx.ds1000DS-1000 dataset annotated with the ground-truth library documentation, to enable evaluations for retrieval and retrieval-augmented code generation.
Please refer to [code-rag-bench] for more details