dmmagdal
/

falcon_7b_GPTQ_4-bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

falcon_7b_GPTQ_4-bit / generation_config.json

dmmagdal's picture

First commit. Uploading model and tokenizer for files for falcon-7b model quantized to 4-bit with GPTQ from auto-gptq

a9f7ec0 9 months ago

history blame contribute delete

No virus

113 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 11,
	"eos_token_id": 11,
	"transformers_version": "4.34.0"
	}