datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
lmsys-chat-1m-qwen2.5-instruct-1024-contextdeepseek-1m-context-benchmark
DeepSeek 1M Context Benchmark
This dataset is the publication-safe measurement release for DeepSeek 1M Context Benchmark: Retrieval Accuracy, Latency, and Cost, version v1.0.0. It contains 344 sanitized terminal API records produced by the frozen protocol deepseek-v4-long-context-retrieval-v1.1.0 during a bounded run from 2026-08-06T20:17:02.706Z through 2026-08-07T00:07:44.737Z.
The study compared deepseek-v4-flash and deepseek-v4-pro on deterministic synthetic English… See the full description on the dataset page: https://huggingface.co/datasets/chatdeepai/deepseek-1m-context-benchmark.Offense_Defense_Organized_4k_Context_1Mmovielens-1m-geo-temporal-context
🤖 LLM-Based Geo-Temporal Context
For experiments using LLM-driven context, we provide scripts and examples to generate geo-temporal context using different LLMs.
📁 Expected Files (Not Included)
geotemporal_context_llama-8b.json
geotemporal_context_llama-70b.json
geotemporal_context_llama-405b.json
Due to licensing and reproducibility considerations, these files are not included in this repository.
Each file is expected to contain:
formatted_date
formatted_location… See the full description on the dataset page: https://huggingface.co/datasets/yejinjennyK/movielens-1m-geo-temporal-context.