Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/models-cards#model-card-metadata)

T5-base data to text model specialized for Finance NLG

simple version

This model was trained on a limited number of indicators, values and dates


Usage (HuggingFace Transformers)

Call the model


from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
  
tokenizer = AutoTokenizer.from_pretrained("yseop/FNP_T5_D2T_simple")

model = AutoModelForSeq2SeqLM.from_pretrained("yseop/FNP_T5_D2T_simple")


text = ["Group profit | valIs | $ 10 && € $10  | dTime | in 2019"]

Choose a generation method



input_ids = tokenizer.encode(": {}".format(text), return_tensors="pt")
p=0.72
k=40

outputs = model.generate(input_ids,
                         do_sample=True,
                        top_p=p,
                        top_k=k,
                        early_stopping=True)

print(tokenizer.decode(outputs[0]))

input_ids = tokenizer.encode(": {}".format(text), return_tensors="pt")

outputs = model.generate(input_ids, 
                         max_length=200, 
                         num_beams=2, repetition_penalty=2.5, 
                         top_k=50, top_p=0.98,
                         length_penalty=1.0,
                         early_stopping=True)

print(tokenizer.decode(outputs[0]))

Created by: Yseop | Pioneer in Natural Language Generation (NLG) technology. Scaling human expertise through Natural Language Generation.

Downloads last month
19
Hosted inference API
This model can be loaded on the Inference API on-demand.

Space using yseop/FNP_T5_D2T_simple