santhosh97
/

gpt-pythia-6.9b-quantized

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

gpt-pythia-6.9b-quantized / generation_config.json

santhosh97's picture

Upload GPTNeoXForCausalLM

92565fb about 2 years ago

history blame contribute delete

116 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 0,
	"eos_token_id": 0,
	"transformers_version": "4.29.0.dev0"
	}