Model Card for new-finetune-flant5-base-model

This model is a fine-tuned version of google/flan-t5-base. It has been trained for multi-task purposes, likely related to job assistance or QA tasks (JobEase project).

Model Details

• Model Type: Text-to-Text Generation (Seq2Seq)
• Base Model: google/flan-t5-base
• Library: Transformers
• Language: English

Training Hyperparameters

The model was fine-tuned with the following hyperparameters:

• Optimization Goal: Multi-task learning
• Epochs: 10
• Batch Size: 8
• Learning Rate: 0.0003
• Transformers Version: 4.57.1

Usage

You can use this model directly with the Hugging Face transformers library:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id = "MMohammad/new-finetune-flant5-base-model"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)

input_text = "Your input text here"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids

outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Installation

pip install transformers torch