ErrLookup › google-research/timesfm

google-research/timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. · Python · 52 source files

Analyzed at 331c6d33cb on 2026-08-29. 37 documented errors.

Code / MessageTypeSeverityTags
Activation: {config.activation} not supported.
validation error config, validation, jax, valueerror
Output dims must be a multiple of 4: {config.output_dims} %
validation error config, validation, shape, valueerror
The embedding dims of the rotary position embeddingmust matc
validation error shape, validation, jax, rotary-embedding
Inputs must be of rank 3 or 4.
validation error shape, validation, jax, tensor-rank
Memory dimension ({self.qkv_features}) must be divisible by
validation error config, shape, attention, valueerror
Incompatible input dimension, got {input_in_features} but mo
validation error shape, attention, validation, dimension-mismatch
Layer norm: {config.attention_norm} not supported.
validation error config, validation, layernorm, valueerror
Layer norm: {config.feedforward_norm} not supported.
validation error config, validation, layernorm, valueerror
Activation: {config.ff_activation} not supported.
validation error config, validation, activation, valueerror
Model is not compiled. Please call compile() first.
exception error python, runtime-state, compile-required
For XReg, `return_backcast` must be set to True in the forec
validation error python, config-mismatch, covariates, xreg
At least one of dynamic_numerical_covariates, dynamic_catego
validation error python, validation, covariates, empty-input
Unsupported mode: {xreg_mode}
validation error python, invalid-argument, enum, xreg
Forecast horizon length inferred from the dynamic covariates
validation error python, validation, covariates, horizon-limit
Context + horizon must be less than the context limit. {fc.m
validation error python, validation, context-limit, config
Continuous quantile head is not supported for horizons > {se
validation error python, validation, quantile, model-capability
Horizon must be less than the max horizon. {horizon} > {fc.m
validation error python, validation, horizon-limit, compile
{self.WEIGHTS_FILENAME} not found in directory {path}
exception error file-not-found, checkpoint-loading, filesystem
{cls.WEIGHTS_FILENAME} not found in directory {model_id}
exception error file-not-found, checkpoint-loading, huggingface
Context + horizon must be less than the context limit. {fc.m
validation error configuration, value-error, context-limit, forecasting
Continuous quantile head is not supported for horizons > {se
validation error configuration, value-error, quantiles, forecasting
Horizon must be less than the max horizon. {horizon} > {fc.m
validation error configuration, value-error, inference, forecasting
Activation: {config.activation} not supported.
validation error configuration, value-error, neural-network, torch
Output dims must be a multiple of 4: {config.output_dims} %
validation error configuration, value-error, neural-network, dimension-mismatch
The embedding dims of the rotary position embeddingmust matc
validation error value-error, shape-mismatch, transformer, torch
Inputs must be of rank 3 or 4.
validation error value-error, shape-mismatch, transformer, torch
Memory dimension ({self.in_features}) must be divisible by '
validation error configuration, value-error, attention, dimension-mismatch, torch
Layer norm: {config.attention_norm} not supported.
validation error python, configuration, valueerror
Layer norm: {config.feedforward_norm} not supported.
validation error python, configuration, valueerror
Activation: {config.ff_activation} not supported.
validation error python, configuration, valueerror
Failed to load the XReg module. Did you forget to install `t
exception error python, importerror, dependencies
Unsupported array shape: {x.shape}
validation error python, numpy, valueerror, shape
train_dynamic_numerical_covariates and test_dynamic_numerica
validation error python, covariates, valueerror, validation
train_dynamic_categorical_covariates and test_dynamic_catego
validation error python, covariates, valueerror, validation
{dict_a_name} has keys not present in {dict_b_name}: {w}
validation error python, covariates, valueerror, validation
{dict_b_name} has keys not present in {dict_a_name}: {w}
validation error python, covariates, valueerror, validation
targets and train_lens must have the same number of elements
validation error python, covariates, valueerror, validation