README.md

metadata

license: mit
widget:
  - example_title: Question Answering!
    text: 'Please Answer the Question: what is depression?'
  - example_title: Other Example!
    text: 'Please Answer the Question: How to bake a cake?'
  - example_title: Other Example!
    text: 'Please Answer the Question: what is depression?'
  - example_title: Other Example!
    text: >-
      Please Answer the Question:  I'm going through some things with my
      feelings and myself.I barely sleep and I do nothing but think about how
      I'm worthless and how I shouldn't be here. I've never tried or
      contemplated suicide. I've always wanted to fix my issues, but I never get
      around to it. How can I change my feeling of being worthless to everyone?
inference:
  parameters:
    do_sample: true
    max_new_tokens: 250
datasets:
  - databricks/databricks-dolly-15k
  - VMware/open-instruct

MaxMini-Instruct-248M

Overview

MaxMini-Instruct-248M is a T5 (Text-To-Text Transfer Transformer) model Instruct fine-tuned on a variety of tasks. This model is designed to perform a range of instruction tasks.

Model Details

• Model Name: MaxMini-Instruct-248M
• Model Type: T5 (Text-To-Text Transfer Transformer)
• Model Size: 248M parameters
• Instruction Tuning

Usage

Installation

You can install the model via the Hugging Face library:

pip install transformers
pip install torch

Inference

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("suriya7/MaxMini-Instruct-248M")
model = AutoModelForSeq2SeqLM.from_pretrained("suriya7/MaxMini-Instruct-248M")

my_question = "what is depression?"
inputs = "Please answer to this question: " + my_question

inputs = tokenizer(inputs, return_tensors="pt"     
                      )

generated_ids = model.generate(**inputs, max_new_tokens=250,do_sample=True)
decoded = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
print(f"Generated Output: {decoded}")