;ijRSSKJr "SS\5r"SS\5r"SS\5rg) )Optimizer1StatecB^\rSrSrSU4SjjrSrU=r$)RMSpropc >US:Xa [S5eU(a [S5e[T U] SUUX64UUUU U U U 5 g)a Base RMSprop optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-2): The learning rate. alpha (`float`, defaults to 0.99): The alpha value is the decay rate of the squared gradients of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. momentum (`float`, defaults to 0): The momentum value speeds up the optimizer by taking bigger steps. centered (`bool`, defaults to `False`): Whether the gradients are normalized by the variance. If `True`, it can help training at the expense of additional compute. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. r)RMSprop with alpha==0.0 is not supported!"Centered RMSprop is not supported!rmspropNNotImplementedErrorsuper__init__)selfparamslralphaeps weight_decaymomentumcentered optim_bitsargs min_8bit_sizepercentile_clipping block_wise __class__s j/home/dmtnaga/Documents/work/airagagent/rag_env/lib/python3.13/site-packages/bitsandbytes/optim/rmsprop.pyrRMSprop.__init__ sYX A:%&QR R %&JK K              ) {Gz?Gz?:0yE>rrF NdT__name__ __module__ __qualname____firstlineno__r__static_attributes__ __classcell__rs@rrrs0   < < rrc@^\rSrSrSU4SjjrSrU=r$) RMSprop8bitHc >US:Xa [S5eU(a [S5e[T U] SUUX64UUSUU U U 5 g)a 8-bit RMSprop optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-2): The learning rate. alpha (`float`, defaults to 0.99): The alpha value is the decay rate of the squared gradients of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. momentum (`float`, defaults to 0): The momentum value speeds up the optimizer by taking bigger steps. centered (`bool`, defaults to `False`): Whether the gradients are normalized by the variance. If `True`, it can help training at the expense of additional compute. 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. rrr r rNr rrrrrrrrrrrrrs rrRMSprop8bit.__init__IsYV A:%&QR R %&JK K             rr r!r"r#rrFNr%r&Tr'r.s@rr0r0Hs-   ; ; rr0c@^\rSrSrSU4SjjrSrU=r$) RMSprop32bitc >US:Xa [S5eU(a [S5e[T U] SUUX64UUSUU U U 5 g)a 32-bit RMSprop optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-2): The learning rate. alpha (`float`, defaults to 0.99): The alpha value is the decay rate of the squared gradients of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. momentum (`float`, defaults to 0): The momentum value speeds up the optimizer by taking bigger steps. centered (`bool`, defaults to `False`): Whether the gradients are normalized by the variance. If `True`, it can help training at the expense of additional compute. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. rrr r r$Nr r3s rrRMSprop32bit.__init__sYX A:%&QR R %&JK K              rr r5r'r.s@rr7r7s-   < < rr7N)bitsandbytes.optim.optimizerrrr0r7r rrr<s0 9= o= @< /< ~= ?= r