cerebras
/

btlm-3b-8k-base

Text Generation

Model card Files Files and versions Community

btlm-3b-8k-base / tokenizer_config.json

Faisal AlKhateeb

add the tokenizer

326d150 10 months ago

raw history blame contribute delete

No virus

234 Bytes

	{
	"add_prefix_space": false,
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 8192,
	"tokenizer_class": "GPT2Tokenizer",
	"unk_token": "<\|endoftext\|>"
	}