nomic-embed-code-W4A16-AWQ / quantization_info.json
pyrymikko's picture
Upload W4A16-AWQ quantized nomic-ai/nomic-embed-code
f8f30e9 verified
{
"original_model": "nomic-ai/nomic-embed-code",
"quantization_scheme": "W4A16",
"group_size": 128,
"compressed_format": "compressed-tensors",
"quantization_method": "llmcompressor-awq",
"weight_bits": 4,
"activation_bits": 16,
"num_calibration_samples": 512
}