← Back to index
v0.2.1 — Add Models
[0.2.1] add models
Added
Progress bars
:
tqdm
integration for visual progress during sequential benchmarking
20 new models
added to
models.txt
(Gemini, Llama, Qwen, Mistral, and more)
Changed
run_benchmark.py
now defaults to
--run-all --sequential
when no arguments provided
Added
tqdm>=4.65.0
to
requirements.txt