transformers/tests/quantization
Marc Sun 8214d6e7b1
add exllamav2 arg (#26437)
* add_ xllamav2 arg

* add test

* style

* add check

* add doc

* replace by use_exllama_v2

* fix tests

* fix doc

* style

* better condition

* fix logic

* add deprecate msg
2023-10-26 10:15:05 -04:00
..
bnb 🚨🚨🚨 [Quantization] Store the original dtype in the config as a private attribute 🚨🚨🚨 (#26761) 2023-10-16 19:56:53 +02:00
gptq add exllamav2 arg (#26437) 2023-10-26 10:15:05 -04:00