ArthurZ
/

gpt_oss_20b_dequantize_quantize

Text Generation

8-bit precision

Model card Files Files and versions

gpt_oss_20b_dequantize_quantize / generation_config.json

ArthurZ's picture

ArthurZ HF Staff

Upload GptOssForCausalLM

49ac667 verified 6 months ago

177 Bytes

	{
	"bos_token_id": 199998,
	"do_sample": true,
	"eos_token_id": [
	200002,
	199999,
	200012
	],
	"pad_token_id": 199999,
	"transformers_version": "4.56.0.dev0"
	}