We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
When trying to load a finetuned model I received the following error:
In [7]: reader = FARMReader(model_name_or_path="model_dir", use_gpu=True) --------------------------------------------------------------------------- TypeError Traceback (most recent call last) <ipython-input-7-44c12407fd4e> in <module> ----> 1 reader = FARMReader(model_name_or_path="model_dir", use_gpu=True) ~/SageMaker/haystack/haystack/reader/farm.py in __init__(self, model_name_or_path, context_window_size, no_ans_threshold, batch_size, use_gpu, n_candidates_per_passage) 51 52 ---> 53 self.inferencer = Inferencer.load(model_name_or_path, batch_size=batch_size, gpu=use_gpu, task_type="question_answering") 54 self.inferencer.model.prediction_heads[0].context_window_size = context_window_size 55 self.inferencer.model.prediction_heads[0].no_ans_threshold = no_ans_threshold ~/SageMaker/FARM/farm/infer.py in load(cls, model_name_or_path, batch_size, gpu, task_type, return_class_probs, strict, max_seq_len) 135 processor = InferenceProcessor.load_from_dir(model_name_or_path) 136 else: --> 137 processor = Processor.load_from_dir(model_name_or_path) 138 139 # b) or from remote transformers model hub ~/SageMaker/FARM/farm/data_handler/processor.py in load_from_dir(cls, load_dir) 188 del config["tokenizer"] 189 --> 190 processor = cls.load(tokenizer=tokenizer, processor_name=config["processor"], **config) 191 192 for task_name, task in config["tasks"].items(): TypeError: load() missing 1 required positional argument: 'data_dir'
I was able to fix this by add "data_dir": "" to the processor_config.json file in the finetuned model directory. The file now looks like this :
"data_dir": ""
{"baskets": [], "data_dir": "", "dev_filename": "dev-v2.0.json", "dev_split": 0, "doc_stride": 128, "max_query_length": 64, "max_seq_len": 256, "ph_output_type": "per_token_squad", "proxies": null, "target": "classification", "tasks": {"question_answering": {"label_list": ["start_token", "end_token"], "metric": "squad", "label_tensor_name": "question_answering_label_ids", "label_name": "question_answering_label", "label_column_name": null, "task_type": null}}, "test_filename": null, "train_filename": "train-v2.0.json", "tokenizer": "DistilBertTokenizer", "processor": "SquadProcessor"}
The text was updated successfully, but these errors were encountered:
Merge pull request #16 from deepset-ai/simpler-base-class
ea586d3
Expose socket related functions
No branches or pull requests
When trying to load a finetuned model I received the following error:
I was able to fix this by add
"data_dir": ""
to the processor_config.json file in the finetuned model directory. The file now looks like this :The text was updated successfully, but these errors were encountered: