Open4bits
/

LFM2.5-1.2B-Base-Quantized

Text Generation

Model card Files Files and versions

LFM2.5-1.2B-Base-Quantized / nf4 /generation_config.json

fmasterpro27's picture

Add NF4 4-bit quantization

25c64d3 verified 18 days ago

history blame contribute delete

132 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 7,
	"pad_token_id": 0,
	"transformers_version": "4.57.3"
	}