Arbiter-8B / generation_config.json

Arbiter v0.4 full model: LoRA merged into the dequantized 4-bit base (fp16), tokenizer, decision head, calibration; adapter kept in adapter/

aa20e73 verified 15 days ago

Raw History Blame Contribute Delete

214 Bytes

{
  "bos_token_id": 151643,
  "do_sample": true,
  "eos_token_id": [
    151645,
    151643
  ],
  "pad_token_id": 151643,
  "temperature": 0.6,
  "top_k": 20,
  "top_p": 0.95,
  "transformers_version": "5.20.2"
}

	{
	"bos_token_id": 151643,
	"do_sample": true,
	"eos_token_id": [
	151645,
	151643
	],
	"pad_token_id": 151643,
	"temperature": 0.6,
	"top_k": 20,
	"top_p": 0.95,
	"transformers_version": "5.20.2"
	}