ek826
/

instruct-gpt-j-fp16-8bit

Text Generation

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

instruct-gpt-j-fp16-8bit / generation_config.json

ek826's picture

Upload GPTJForCausalLM

ed6a75b over 1 year ago

history blame contribute delete

119 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 50256,
	"eos_token_id": 50256,
	"transformers_version": "4.28.1"
	}