prithivMLmods/Open-Xi-Math-Preview

Open-Xi-Math-Preview

Open-Xi-Math-Preview is a mathematics-focused reasoning model fine-tuned on Qwen2-1.5B-Instruct, utilizing a modular dataset designed for enhancing mathematical thinking. It provides robust capabilities in symbolic reasoning, structured deduction, and compact coding — optimized for edge deployment on resource-constrained devices.

Key Improvements

1. 1.Mathematical Reasoning via Modular Data: Fine-tuned on diverse and structured math-focused datasets to handle problem-solving, symbolic computation, and multi-step derivations with efficiency on low-power devices.

1. 1.Compact Coding & Math Assistant: Understands multiple programming languages and math representations (e.g., LaTeX, symbolic algebra). Ideal for math-enhanced embedded coding and problem-solving environments.

1. 1.Error Detection in Structured Data: Accurately detects and corrects logical errors, malformed math expressions, and data structures (e.g., JSON, XML, LaTeX), all while maintaining low inference latency.

1. 1.Instruction Following for Problem-Solving: Enhanced with strong instruction-following performance, particularly for step-wise solutions in math word problems, logic puzzles, and equation derivations.

1. 1.Extended Context Support: Supports 128K token inputs and 8K token outputs, enabling it to work with long math chains-of-thought and proofs, while remaining lightweight enough for edge inference.

Quickstart with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "your-username/Open-Xi-Math-Preview"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Solve the equation: 2x^2 - 4x - 6 = 0. Show all steps."
messages = [
    {"role": "system", "content": "You are a helpful and concise mathematical reasoning assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Intended Use

1. 1.Math-Centric Edge Applications: Designed for embedded AI systems in calculators, educational tools, and mobile math tutoring.

1. 1.Advanced Math Reasoning: Effective for solving algebra, geometry, calculus, and competition math problems using logical derivation.

1. 1.Educational & Instructional Aids: Useful for step-by-step teaching in math-heavy domains like STEM education, coding classes, and robotics kits.

1. 1.Low-Latency Math Agents: Deployable in customer support bots, interactive kiosks, and STEM-based IoT systems for fast math-based interactions.

1. 1.Structured Output Generation: Generates LaTeX, JSON, or tabular formats for math answers and reasoning in structured pipelines.

Limitations

1. 1.Edge Hardware Still Required: Though lightweight, best used with devices equipped with NPUs, GPUs, or optimized ML accelerators.

1. 1.No Internet or Real-Time Info: Static knowledge cutoff; cannot retrieve or interact with live external data sources.

1. 1.Not Suited for Creative Tasks: Focused on deterministic reasoning — not built for abstract, poetic, or generative creative writing.

1. 1.Prompt Sensitivity: Clear, structured prompts yield more accurate reasoning; ambiguous questions may degrade output quality.

1. 1.Potential Dataset Biases: Model may carry forward biases or inconsistencies present in the training datasets; vet outputs in critical settings.