deepankar27

@lajanugen I have able to create the model but now I cannot load it using : `encoder.load_model(configuration.model_config(modl), vocabulary_file=VOCAB_FILE, embedding_matrix_file=EMBEDDING_MATRIX_FILE, checkpoint_path=CHECKPOINT_PATH)` Where modl contain the eval json, I am quite clueless...

Any update on this? Even evealuate.py is using from functions like eval_sick which is not available in the repo... @lajanugen please assist on this..

@spate141 @ni9elf @richliao Do you people have any update on the visualization part, can you guys help on this?

@spate141 Thanks!! looks like a nice tool but how will I feed my model's attention values to it along with predicted model score for each label but how can I...

@spate141 Awesome!! Thanks a lot!!

I am also getting same exception. Did you get how to resolve this?

add with torch.autocast("cuda"): and it will work. ``` with torch.autocast("cuda"): inputs = tokenizer(prompt, return_tensors="pt") input_ids = inputs["input_ids"].to("cuda") with torch.no_grad(): generation_output = model.generate( input_ids=input_ids, generation_config=generation_config, return_dict_in_generate=True, output_scores=True, max_new_tokens=100 ) for s...