How can I update knowledge of a model already trained before? (ValueError: Unrecognized model)

[John6666]

The immediate cause is that config.json cannot be found. There are several possible reasons for this, but if the repository was created with AutoTrainAdvanced, it may be because only the adapter is saved instead of the entire model.

Resources

does not appear to have a file named config.json

How to reload the checkpoints for LLM finetuning?

Trainer .train (resume _from _checkpoint =True)

Hi all, I’m trying to resume my training from a checkpoint my training argument: training_args = TrainingArguments( output_dir=repo_name, group_by_length=True, per_device_train_batch_size=16, per_device_eval_batch_size=1, gradient_accumulation_steps=8, evaluation_strategy=“steps”, num_train_epochs=50, fp16=True, save_steps=500, eval_steps=400, logging_steps=10, learning_rate=5e-4, warmup_steps=3000, push_to_hub=True, ) my trainer: trainer = Trainer( model=model, data_collat…