+ Lj7Rt^RIt^RIHt^RIHtHt^RIHt^RI H t ^RI H t H t HtHtHtHtHtHt^RIHt^RIHtR ]R ]R ]R ]R ]R] R]/tR ] R ] R ]R ]R ]R]R] /t!RR4tR#)z Adapted from https://github.com/huggingface/transformers/blob/c409cd81777fb27aadc043ed3d8339dbc020fb3b/src/transformers/quantizers/auto.py N)AutoRoundQuantizer)BnB4BitDiffusersQuantizerBnB8BitDiffusersQuantizer) GGUFQuantizer)NVIDIAModelOptQuantizer)AutoRoundConfigBitsAndBytesConfigGGUFQuantizationConfigNVIDIAModelOptConfigQuantizationConfigMixinQuantizationMethod QuantoConfig TorchAoConfig)QuantoQuantizer)TorchAoHfQuantizerbitsandbytes_4bitbitsandbytes_8bitggufquantotorchaomodeloptz auto-roundca]tRt^>>c VPRR4pVPRR4'gVPRR4'd5VPRR4'dRMRp\PV,pMVf \R4hV\P 49d-\RV R \ \P 44 24h\V,pVPV4#) quant_methodN load_in_8bitF load_in_4bit_4bit_8bitzThe model's quantization config from the arguments has no `quant_method` attribute. Make sure that the model has been correctly quantizedUnknown quantization type, got  - supported types are: ) getr BITS_AND_BYTES ValueError AUTO_QUANTIZATION_CONFIG_MAPPINGkeyslistAUTO_QUANTIZER_MAPPING from_dict)clsrr$suffix target_clss&& rr2 DiffusersAutoQuantizer.from_dictBs/33NDI # ' ' > >BZB^B^_motBuBu 8 < <^U S SWY`F-<>(990 4 4'#'#r"r)r[rN autoroundr bitsandbytesrrrrrrr8rrr r r r r rrrrrr1r.rrVr"rras )N-   $'22 M o !'$++ " l }$/$ j#j#r"