Yeo Wei Jie
Yeo Wei Jie
asking about this as well.
@baptistejamin, do you have to specify the splits? so data_dir is only the dir? how would it find prompt.jsonl then?
i do not know why, but i keep getting error "FileNotFoundError: Unable to find '/workspace/scripts/train/train' at /workspace/scripts/train" at `dataset = datasets.load_dataset(dataset_name, split=split, **kwargs)` my yaml is `# Dataloaders train_loader: name:...
from multiagent.core import World, Agent, Landmark ModuleNotFoundError: No module named 'multiagent'
is ther any solutions to this?
This is true, i have tried SFT using the script above. And the model does not learn how to stop generating. The sft script uses the default DataCollatorForLanguageModelling and if...
Hi, can i clarify regarding in `rep_control_pipeline.py `, how is self.wrapped_model used? during the init fn: ` self.wrapped_model = WrappedReadingVecModel(model, tokenizer) self.wrapped_model.unwrap() self.wrapped_model.wrap_block(layers, block_name=block_name) self.block_name = block_name self.layers = layers...
it shows `outputs = wrapped_model(**encoded_inputs.to(model.device), output_hidden_states=True)['hidden_states']`, but the outputs are overriden by the later model.generate also, if i use wrappedmodel.generate, it doesn't take in other generate args such as do_sample,...
Hi, i got the same error as well. `results = [] date = None for row in rows: # raw_timestamp = row.xpath("./td")[0].xpath("text()")[0][0:-2] raw_timestamp = str(row.xpath("./td")[0].xpath("text()")[0][0:-2]).strip() # if len(raw_timestamp) > 8:...