You can deploy this model and start earning money today!

woyeso/
fine_tuned_llama_3_2_assignment_grader

Name: fine_tuned_llama_3_2_assignment_grader
Availability: InStock

peft

safetensors

llama3.2

Views

No views yet

Framework versions

PEFT 0.15.2

Fine-Tuned LLaMA-3.2 Assignment Grader

This model is a fine-tuned version of the LLaMA-3.2-3B-Instruct-bnb-4bit model, developed to automatically grade student assignments based on rubric scores (0-10). It supports both group and individual project assessments.

Model Details

Base Model: LLaMA-3.2-3B-Instruct-bnb-4bit
Fine-Tuning Task: Classification/Regression for rubric scores
Dataset: 150 student responses (group and individual projects)
Quantization: 4-bit precision for efficiency
Max Sequence Length: 2048 tokens

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "your-username/fine_tuned_llama_3_2_assignment_grader"
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Generate predictions
input_text = "Sample student response text here."
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))

woyeso/fine_tuned_llama_3_2_assignment_grader

Framework versions

Fine-Tuned LLaMA-3.2 Assignment Grader

Model Details

Usage

woyeso/
fine_tuned_llama_3_2_assignment_grader