MCPcopy
hub / github.com/modelscope/ms-swift / test_llm_quant

Function test_llm_quant

tests/export/test_quant.py:7–14  ·  view source on GitHub ↗
(quant_method: Literal['gptq', 'awq'] = 'awq')

Source from the content-addressed store, hash-verified

5
6
7def test_llm_quant(quant_method: Literal['gptq', 'awq'] = 'awq'):
8 from swift import ExportArguments, export_main
9 export_main(
10 ExportArguments(
11 model='Qwen/Qwen2-7B-Instruct',
12 quant_bits=4,
13 dataset=['AI-ModelScope/alpaca-gpt4-data-zh#1000', 'AI-ModelScope/alpaca-gpt4-data-en#1000'],
14 quant_method=quant_method))
15
16
17def test_vlm_quant(quant_method: Literal['gptq', 'awq'] = 'awq'):

Callers

nothing calls this directly

Calls 2

export_mainFunction · 0.90
ExportArgumentsClass · 0.90

Tested by

no test coverage detected