reverted tokenizer fix, will be solved manually upon testing, current evals 5213c6c Yeyito commited on Dec 20, 2023
We use the same code in here to test the models outside of this space 20ed3ea Yeyito commited on Dec 19, 2023
More aggressive OOM prevention, num_z reduced to 50 for gsm8k and mmlu 98282cd Yeyito commited on Dec 19, 2023
Avoiding re-loading already loaded models. Stated unload functionality as not-implemented. b28ad14 Yeyito commited on Dec 19, 2023