radu/LLamaRecipes

réplica de https://github.com/facebookresearch/llama-recipes.git

Autor	SHA1 Mensaxe	Data
Jeff Tang	5baa1e3fd7 vllm enabled eval for HF and fine-tuned models; code cleanup and refactoring for text2sql_eval; minimum eval packages for eval requirements; merge peft script to make vllm happy	hai 3 meses
Amir Youssefi	e10ddda64a some refactoring and cleaning	hai 3 meses
Amir Youssefi	6b92409507 dynamically calculating max tokens param; it was unused before	hai 3 meses
Jeff Tang	9ac5dd12fb make max_tokens same - 10240	hai 3 meses
Jeff Tang	f7c68c1003 bug fix on loading PEFT and FFT model for eval	hai 3 meses
Jeff Tang	6815255595 folder struc refactoring	hai 4 meses