Raptor-X2 is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. This model is optimized for advanced mathematical explanations, scientific reasoning, and general-purpose coding. It excels in contextual understanding, logical deduction, and multi-step problem-solving. Raptor-X2 has been fine-tuned using a long chain-of-thought reasoning model and specialized datasets to improve comprehension, structured responses, and conversational intelligence.

Key improvements include:

Enhanced Mathematical Reasoning: Provides step-by-step explanations for complex mathematical problems, making it useful for students, researchers, and professionals.
Advanced Scientific Understanding: Excels in explaining scientific concepts across physics, chemistry, biology, and engineering.
General-Purpose Coding: Capable of generating, debugging, and optimizing code across multiple programming languages, supporting software development and automation.
Long-Context Support: Supports up to 128K tokens for input context and can generate up to 8K tokens in a single output, making it ideal for detailed responses.
Multilingual Proficiency: Supports over 29 languages, including English, Chinese, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.

Quickstart with transformers

Here is a code snippet with apply_chat_template to show you how to load the tokenizer and model and generate content:

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Raptor-X2"

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

prompt = "Explain the fundamental theorem of calculus."
messages = [
    {"role": "system", "content": "You are a helpful assistant capable of answering a wide range of questions."},
    {"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

Mathematical Explanation:
Designed for providing step-by-step solutions to mathematical problems, including algebra, calculus, and discrete mathematics.
Scientific Reasoning:
Suitable for explaining scientific theories, conducting physics simulations, and solving chemistry equations.
Programming and Software Development:
Capable of generating, analyzing, and optimizing code in multiple programming languages.
Educational Assistance:
Helps students and researchers by providing explanations, summaries, and structured learning material.
Multilingual Applications:
Supports global communication, translations, and multilingual content generation.
Long-Form Content Generation:
Can generate extended responses, including research papers, documentation, and technical reports.

Limitations

Hardware Requirements:
Requires high-memory GPUs or TPUs due to its large parameter size and long-context support.
Potential Bias in Responses:
While designed to be neutral, outputs may still reflect biases present in training data.
Complexity in Some Scientific Domains:
While proficient in general science, highly specialized fields may require verification.
Limited Real-World Awareness:
Does not have access to real-time events beyond its training cutoff.
Error Propagation in Extended Outputs:
Minor errors in early responses may affect overall coherence in long-form outputs.
Prompt Sensitivity:
The effectiveness of responses may depend on how well the input prompt is structured.