transformers/tests/quantization
Younes Belkada 3f435823e0
FEAT / Bitsandbytes: Add `dequantize` API for bitsandbytes quantized models (#30806)
* add  method

* change method name

* more comments

* Apply suggestions from code review

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* fixup

* add docstrings and fix comment

* warn users on the de-quantized dtype

* Update src/transformers/quantizers/base.py

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* Update src/transformers/integrations/bitsandbytes.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* final suggestion - use private method

---------

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-05-15 17:17:09 +02:00
..
aqlm_integration Cache: Static cache as a standalone object (#30476) 2024-04-30 16:37:19 +01:00
autoawq [awq] replace scale when we have GELU (#30074) 2024-05-13 11:41:03 +02:00
bnb FEAT / Bitsandbytes: Add `dequantize` API for bitsandbytes quantized models (#30806) 2024-05-15 17:17:09 +02:00
eetq_integration [FEAT]: EETQ quantizer support (#30262) 2024-04-22 20:38:58 +01:00
ggml Loading GGUF files support (#30391) 2024-05-15 14:28:20 +02:00
gptq [GPTQ] Fix test (#28018) 2024-01-15 11:22:54 -05:00
hqq Quantization / HQQ: Fix HQQ tests on our runner (#30668) 2024-05-06 11:33:52 +02:00
quanto_integration [Quantization] Quanto quantizer (#29023) 2024-03-15 11:51:29 -04:00