Organization

Green Lab

Green-Lab

Models in Library0

Datasets in Library1

Models on Hugging Face1

Followers2

Compare the published evidence

This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Text generation.

Reported licenses: cc-by-4.0. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Datasets

Dataset · Text generation

cc-traces-weka-minimax-v4

Green Lab

223 agentic coding sessions in Weka KV-Cache-Tester format, recorded against minimax-m2.5 (17,672 streaming requests, no subagents, blocksize 64, hashidscope: local, max input ~186k tokens). Each.json holds one session: requests[] with timestamp t, input/output token counts, hashids (KV-cache block IDs) and thinktime. No prompt text is included; prompts are reconstructed from hashids at replay time.

Publicly accessible cc-by-4.0

View dataset