patrickbdevaney
/

llama-xlam-8b-fc-4bit

Model card Files Files and versions

llama-xlam-8b-fc-4bit / quantize_config.json

patrickbdevaney's picture

patrickbdevaney

4bit quant of salesforce xlam 8b fc

70b9105 10 months ago

history blame contribute delete

95 Bytes

{"q_group_size": 128, "w_bit": 4, "zero_point": true, "version": "GEMM", "quant_method": "awq"}