model-scope
/

glm-4-9b-chat-GPTQ-Int8

Text Generation

feature-extraction

8-bit precision

Model card Files Files and versions Community

glm-4-9b-chat-GPTQ-Int8 / generation_config.json

tclf90

'优化模型量化损失'

40945b7 5 months ago

history blame contribute delete

129 Bytes

	{
	"_from_model_config": true,
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"transformers_version": "4.40.2"
	}