README.md

metadata

language: en
license: apache-2.0
tags:
  - mathematics
  - chain-of-thought
  - question-answering

KnullAI v2 - Fine-tuned on GAIR/o1-journey

This model is a fine-tuned version of KnullAI v2, specifically trained on mathematical problem-solving using the GAIR/o1-journey dataset.

Training Data

The model was fine-tuned on the GAIR/o1-journey dataset, which contains:

• Mathematical questions
• Detailed answers
• Step-by-step explanations (Chain of Thought)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained("Rawkney/knullAi_v2")
tokenizer = AutoTokenizer.from_pretrained("Rawkney/knullAi_v2")

# Example usage
question = "What is the area of a triangle with vertices at (0,0), (3,0), and (0,4)?"
input_text = f"Question: {question}\nAnswer:"
inputs = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(
    inputs["input_ids"],
    max_length=512,
    temperature=0.7,
    top_p=0.9
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Procedure

• Fine-tuned using the Transformers library
• Training parameters:
  • Learning rate: 2e-5
  • Epochs: 3
  • Batch size: 2
  • Gradient accumulation steps: 4
  • Mixed precision training (fp16)