Files

T

Benjamin Bossan 250b7eb85f FEAT Show adapter layer and model status (#1663 )

This PR adds a new feature to PEFT models that allows to better
understand the status of adapter(s) on the model. Quoting from the doc
entry that I added:

Sometimes, the PEFT model can end up in a bad state, especially when
handling multiple adapters. There can be some confusion around what
adapters exist, which one is active, which one is merged, etc. To help
investigate this issue, you can call the
get_layer_status and the
get_model_status methods. The first one gives you a
detailed overview about the adapters for each targeted layer. The latter
one gives you a high-level overview about the model status.

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

2024-04-29 13:31:23 +02:00

1.6 KiB

Raw Permalink Blame History

Models

[PeftModel] is the base model class for specifying the base Transformer model and configuration to apply a PEFT method to. The base PeftModel contains methods for loading and saving models from the Hub.

PeftModel

autodoc PeftModel - all

PeftModelForSequenceClassification

A PeftModel for sequence classification tasks.

autodoc PeftModelForSequenceClassification - all

PeftModelForTokenClassification

A PeftModel for token classification tasks.

autodoc PeftModelForTokenClassification - all

PeftModelForCausalLM

A PeftModel for causal language modeling.

autodoc PeftModelForCausalLM - all

PeftModelForSeq2SeqLM

A PeftModel for sequence-to-sequence language modeling.

autodoc PeftModelForSeq2SeqLM - all

PeftModelForQuestionAnswering

A PeftModel for question answering.

autodoc PeftModelForQuestionAnswering - all

PeftModelForFeatureExtraction

A PeftModel for getting extracting features/embeddings from transformer models.

autodoc PeftModelForFeatureExtraction - all

PeftMixedModel

A PeftModel for mixing different adapter types (e.g. LoRA and LoHa).

autodoc PeftMixedModel - all

Utilities

autodoc utils.cast_mixed_precision_params

autodoc get_peft_model

autodoc inject_adapter_in_model

autodoc utils.get_peft_model_state_dict

autodoc utils.prepare_model_for_kbit_training

autodoc get_layer_status

autodoc get_model_status

1.6 KiB Raw Permalink Blame History