huggingface/transformers

Documented errors, page 2 of 6. Back to huggingface/transformers

Code / MessageTypeSeverityTags
tp_size ( ) * fsdp_size ( ) is not equal to world_size ( )
exception error distributed, fsdp, tensor-parallel, world-size, config
You need to install optimum-quanto in order to use KV cache…
exception error dependencies, quantization, kv-cache, import-error
`temperature` (= ) has to be a strictly positive float…
validation error generation, sampling, temperature, argument-validation
Expert parallelism was requested…
exception error distributed, expert-parallelism, moe, tensor-parallelism
Memory footprint is more than available memory
exception critical memory, continuous-batching, kv-cache, configuration
Unsupported tensor parallel style
exception error tensor-parallel, distributed, config, validation
Conv3dToLinear expects a 5D or 2D tensor, got
exception error weight-conversion, conv3d, model-loading, shape-mismatch
Some generation parameters are set in the model config…
validation error config, generation, save, migration
0 in strides is not supported for ExecuTorch.
exception error export, executorch, strides, tensor-ops
head_dim or (hidden_size and num_attention_heads) could not…
validation error continuous-batching, kv-cache, model-config, head-dim
`skip` must be an iterable of strings.
exception error heterogeneity, config, type-validation, per-layer
Unsupported number of image dimensions
validation error image-processing, shape-validation, channel-dimension
Fix these issues to save the configuration.
validation error generation-config, save, validation
GroupWeightRename requires N:N length matching, but found…
exception error weight-conversion, rename, validation, programmer-error
is not a valid model name
validation error cli, valueerror, add-new-model, model-type, developer-tooling
None of the available devices `available_devices =
exception error
All of the arguments --batch-size, --sequence-length, and…
exception error deepgemm, fp8, block-quantization, checkpoint-config
only support DDP optuna HPO for ParallelMode.DISTRIBUTED…
exception error hpo, optuna, distributed, trainer
Invalid image type. Expected either PIL.Image.Image…
validation error image-processing, type-checking, argument-validation
GenerationConfig is invalid
validation error generation-config, validation, save, strict-mode
out_features must not contain any duplicates, got
exception error backbone, configuration, validation, duplicates
out_indices must be a list, got
exception error config, backbone, validation, type-error
StoppingCriteria needs to be subclassed
exception error stopping-criteria, abstract-class, generation, subclassing
This model does not support the quantized cache. If you…
validation error generation, cache, quantized-cache, encoder-decoder, unsupported-feature
Unsupported forward dtype
exception error fp-quant, quantization, config, dtype, validation
Model has no config_class or model_type.
validation error kernels, model-registration, config-class, custom-model
Received multiple types, therefore expected the first type…
exception error gguf, ggml, metadata-parsing, file-corruption
reference must be greater than zero
exception error audio, validation, decibels, numerical
Worker process information is not available for seeding the…
validation error data-collator, dataloader, multiprocessing, randomness, seed
does not have a FSDP2 plan declared. Set…
exception error distributed, fsdp2, model-integration, sharding
does not implement `export`. Pick a concrete exporter…
exception error export, not-implemented, abstract-method, plugin
Module does not have the expected child modules required…
validation error hub-kernels, fusion, pattern-matching
Unknown error
exception error cli, chat, serving, model-loading, runtimeerror
This modeling file requires the following packages that…
exception error dependencies, trust-remote-code, environment, import
`typical_p` has to be a float > 0 and < 1, but is
validation error generation, typical-sampling, typical-p, argument-validation
`crop` was called, but the current layer does not track…
exception error cache, linear-attention, generation, rollback, runtimeerror
Framework ' ' not recognized!
exception error data-collator, return-tensors, api-misuse, framework
Generated tokens, expected
exception error deepgemm, fp4, gpu-architecture, hopper, blackwell
You passed `inputs_embeds` to `.generate()`, but the model…
validation error generate, inputs-embeds, model-architecture, custom-model
Found ' ' in inputs. Loss computation is not supported…
exception error export, inputs, training-data, validation
Loading this model requires you to execute custom code…
exception error trust-remote-code, security, interactive, timeout
out_features must be a list got
exception error backbone, configuration, validation, type-error
`kernels` is either not installed or uses an incompatible…
exception error dependencies, kernels, attention, version-mismatch
out_features must be a subset of stage_names
exception error backbone, configuration, validation, naming
Unknown logit_processor_kwargs
validation error validation, logits-processor, generation-config, continuous-batching
m must be provided if max_batch_tokens and num_blocks are…
validation error continuous-batching, memory-planning, configuration, validation
return_tensors must be one of ("pt", "np")
validation error data-collator, sequence-packing, return-tensors, configuration
The main model and the assistant don't have compatible…
validation error generation, assisted-decoding, encoder-decoder, whisper, model-loading
Expected class name to start with Gemma4 or Gemma3n. Got
validation error generate, assisted-generation, gemma, model-compatibility, mtp
` ` does not contain a `custom_generate` subdirectory with…
exception error hub, custom-code, generate, remote-code, offline
You need to install `HQQ` in order to use KV cache…
exception error dependencies, quantization, kv-cache, import-error
`axis_key` for `HQQ` backend has to be one of [`0`, `1`]…
validation error quantization, kv-cache, config, validation
An error occurred while trying to load from
validation error huggingface-hub, kernels, network, repo-not-found, wrapped-error
Can't load image processor for
exception error
Training label is not a string
validation error xnli, data-processing, labels, validation
Workspace must be set before calling forward
exception error quantization, higgs, vllm-kernel, missing-setup, runtime-state
You are using `from_pretrained` with a meta device context…
exception error
Invalid checkpoint path
exception error security, path-traversal, tooling, tokenizer
.export failed on component ' ' (submodel= , input keys= ).
exception error export, generation, wrapper-exception, debugging
Unsupported export config
exception error export, config, registry, auto-class
decompose_multimodal failed for
exception error export, multimodal, inputs, transformers
decompose_prefill_decode expected at least
exception error export, generation, architecture, transformers
Per-component `config` dict is missing entries for
exception error export, generation, config, validation
The current `device_map` had weights offloaded to the disk…
validation error
This collator requires that sequence lengths be even to…
validation error data-collator, padding, sequence-length, permutation-language-modeling
Whole word masking can only be used with mlm=True.If you…
validation error data-collator, configuration, masked-language-modeling
`axis_value` for `HQQ` backend has to be one of [`0`, `1`]…
validation error quantization, hqq, cache, validation, valueerror
Found 'model.config.return_loss=True'. Loss computation is…
exception error export, config, loss, transformers
mlm_probability should be between 0 and 1.
validation error data-collator, mlm, validation, probability, training
out_indices must not contain any duplicates, got
exception error config, backbone, validation, duplicates
You're trying to run a `Unigram` model but you're file was…
exception error tokenizer, sentencepiece, conversion
`axis_key` for `quanto` backend has to be one of [`0`…
validation error quantization, kv-cache, config, validation
Expected assistant_model to be a Gemma4AssistantForCausalLM…
validation error python, transformers, generation, speculative-decoding, gemma4, assistant-model
The ` ` entries must be in but got
validation error config, architecture, layer-types, validation
Expected to be 4 or 6.
validation error cache, encoder-decoder, ddp, data-layout, valueerror
save_pretrained(..., distributed_checkpoint=True) requires…
exception error fsdp, distributed, device-mesh, initialization
Unknown modality for
exception error serving, model-registry, modality, valueerror, custom-model
All patterns for a fused kernel must share the same parent…
validation error hub-kernels, fusion, kernel-config
mode is not a valid split name
validation error glue, deprecated, dataset, split-name, keyerror
The model vocabulary size is
validation error generation, sequence-bias, vocabulary, token-ids
This tokenizer does not have a mask token which is…
exception error data-collator, mlm, tokenizer, mask-token, training
We tried to initialize torch.distributed for you, but it…
exception error distributed, process-group, environment, launch
Text and labels have mismatched lengths
validation error data-processing, validation, length-mismatch
This tokenizer does not have a mask token which is…
validation error data-collator, tokenizer, masked-language-modeling, sop
requires newer versions of
exception error export, dependencies, version-mismatch, environment
CB worker died during request
http critical serving, continuous-batching, crash, oom, http-503
It looks like the config file at
exception error generation-config, json, cache, loading, corruption
Cannot specify both default_to_square=True and max_size
exception error image-processing, config, resize, valueerror
FSDP+TP is not supported yet. Use…
exception error distributed, fsdp, tensor-parallelism, configuration
PUSH_TO_HUB_TOKEN is not set, cannot push results to the…
exception error deepgemm, tensor-shape, scale-factor, validation
You have modified the pretrained model configuration to…
validation error generation, generation-config, legacy-migration, breaking-change
Setting `assistant_ensemble_weight` requires candidate…
validation error generate, assisted-generation, speculative-decoding, prompt-lookup, config-conflict
`sequence_bias` has to be a non-empty dictionary, or…
validation error generation, sequence-bias, argument-validation
You must provide only one of `prefix_to_add` and…
exception error weight-conversion, rename, prefix, validation, programmer-error
Fusion for model type conflicts with an existing conversion…
exception error python, transformers, fusion, weight-conversion, conflict
Incorrect audio source. Must be a valid URL starting with…
exception error deepgemm, moe, static-quantization, fp8
not supported filetype
exception error deepgemm, multi-gpu, device-map, moe, parallelism
Tensor query has shape with a zero…
exception error flash-attention, attention, empty-tensor, shape-validation
The model's config file has neither `hidden_size` nor…
validation error
Complex-valued input waveforms are not currently supported
exception error audio, stft, dtype-error