TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Python
fix: improve PEFT device consistency and XReg output slicing
darkpowerxo18d5eb2d441e
diff --git a/peft/adapters.py b/peft/adapters.pyindex 951cfe1..acc6eee 100644--- a/peft/adapters.py+++ b/peft/adapters.py@@ -110,9 +110,10 @@ class DoRALinear(nn.Module):in_f = base_linear.in_featuresout_f = base_linear.out_features+ dev = base_linear.weight.device- self.lora_A = nn.Parameter(torch.empty(in_f, rank))- self.lora_B = nn.Parameter(torch.zeros(rank, out_f))+ self.lora_A = nn.Parameter(torch.empty(in_f, rank, device=dev))+ self.lora_B = nn.Parameter(torch.zeros(rank, out_f, device=dev))nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))# Magnitude vector — initialised from pretrained column norms.@@ -272,7 +273,8 @@ def load_adapter_weights(model: nn.Module, path: str) -> None:The model must already have adapters injected (via ``inject_adapters``)before calling this function."""- tensors = load_file(path, device="cpu")+ device = str(next(model.parameters()).device)+ tensors = load_file(path, device=device)trainable = {n for n, p in model.named_parameters() if p.requires_grad}missing = trainable - set(tensors.keys())if missing:diff --git a/src/timesfm/utils/xreg_lib.py b/src/timesfm/utils/xreg_lib.pyindex 4355261..2759b67 100644--- a/src/timesfm/utils/xreg_lib.py+++ b/src/timesfm/utils/xreg_lib.py@@ -509,9 +509,9 @@ class BatchedInContextXRegLinear(BatchedInContextXRegBase):@ x_tr_j.T@ y_tr_j)- outputs.append(np.array(x_te_j @ beta_hat))+ outputs.append(np.array(x_te_j @ beta_hat)[:tel])if debug_info:- outputs_context.append(np.array(x_tr_raw_j @ beta_hat))+ outputs_context.append(np.array(x_tr_raw_j @ beta_hat)[:trl])train_idx += trltest_idx += tel