Qwen
/

Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8 / generation_config.json

feihu.hf

upload weights

66704b6 3 months ago

117 Bytes

	{
	"bos_token_id": 151643,
	"eos_token_id": 151643,
	"max_new_tokens": 2048,
	"transformers_version": "4.39.3"
	}