;i]-SSKJr "SS\5r"SS\5r"SS\5r"SS \5r"S S \5r"S S \5rg))Optimizer1Statec>^\rSrSrSU4SjjrSrU=r$)Lionc 6>[T U]SUUUSUUUUUU U S9 g)a Base Lion optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-4): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. weight_decay (`float`, defaults to 0): The weight decay value for the optimizer. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. lionis_pagedNsuper__init__) selfparamslrbetas weight_decay optim_bitsargs min_8bit_sizepercentile_clipping block_wiser __class__s g/home/dmtnaga/Documents/work/airagagent/rag_env/lib/python3.13/site-packages/bitsandbytes/optim/lion.pyr Lion.__init__ s<L              ) -C6?g?gGz?r NdTF__name__ __module__ __qualname____firstlineno__r__static_attributes__ __classcell__rs@rrrs*  3 3 rrc<^\rSrSrSU4SjjrSrU=r$)Lion8bit?c 6>[T U]SUUUSUSUUUUU S9 g)aX 8-bit Lion optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-4): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. weight_decay (`float`, defaults to 0): The weight decay value for the optimizer. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. rr rr Nr rrrrrrrrrr rs rrLion8bit.__init__@s<F             rrrrrNr!r"TFr#r*s@rr,r,?'  0 0 rr,c<^\rSrSrSU4SjjrSrU=r$) Lion32bitsc 6>[T U]SUUUSUSUUUUU S9 g)aY 32-bit Lion optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-4): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. weight_decay (`float`, defaults to 0): The weight decay value for the optimizer. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. rr r r Nr r/s rrLion32bit.__init__ts<F              rrr1r#r*s@rr4r4sr2rr4c<^\rSrSrSU4SjjrSrU=r$) PagedLionc 6>[T U]SUUUSUUUUUU SS9 g)aL Paged Lion optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-4): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. weight_decay (`float`, defaults to 0): The weight decay value for the optimizer. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. rr Tr Nr ) rrrrrrrrrrrs rrPagedLion.__init__s<F              rr)rrrr Nr!r"Tr#r*s@rr9r9s'  0 0 rr9c:^\rSrSrSU4SjjrSrU=r$) PagedLion8bitc 6>[T U]SUUUSUSUUUUSS9 g)aR Paged 8-bit Lion optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-4): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. weight_decay (`float`, defaults to 0): The weight decay value for the optimizer. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. rr rTr Nr rrrrrrrrrrs rrPagedLion8bit.__init__s<D             rrrrrNr!r"Tr#r*s@rr>r>$  / / rr>c:^\rSrSrSU4SjjrSrU=r$)PagedLion32bitic 6>[T U]SUUUSUSUUUUSS9 g)aS Paged 32-bit Lion optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-4): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. weight_decay (`float`, defaults to 0): The weight decay value for the optimizer. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. rr r Tr Nr rAs rrPagedLion32bit.__init__s<D              rrrCr#r*s@rrFrFrDrrFN)bitsandbytes.optim.optimizerrrr,r4r9r>rFrrrrJsW 94 ?4 n1 1 h1 1 h1 1 h0 O0 f0 _0 r