QuantiPhy
/

gpt-neo-2.7B-4bit-quantized

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

gpt-neo-2.7B-4bit-quantized / generation_config.json

QuantiPhy's picture

Upload GPTNeoForCausalLM

56a7e1a verified 4 months ago

No virus

119 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 50256,
	"eos_token_id": 50256,
	"transformers_version": "4.41.2"
	}