Ophiuchi Qwen3 14B Instruct

🚀 Ophiuchi-Qwen3-14B-Instruct

Ophiuchi-Qwen3-14B-Instruct is built upon the Qwen3-14B architecture. It uses the Qwen3ForCausalLM backbone and is instruction-tuned to enhance capabilities in mathematical reasoning, code generation, and factual accuracy. It can excel in solving complex reasoning tasks and generating accurate, structured content across multiple domains.

🚀 Quick Start

Quickstart with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Ophiuchi-Qwen3-14B-Instruct"

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

prompt = "Explain the principles of alignment in large language models."

messages = [
    {"role": "system", "content": "You are a highly capable assistant focused on reasoning, coding, and factual precision."},
    {"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]
print(response)

✨ Features

1. Mathematical and Logical Reasoning: Fine-tuned to perform step-by-step reasoning, symbolic logic, and advanced mathematics, supporting educational and technical use cases.
2. Code Generation and Understanding: Optimized for writing, interpreting, and debugging code across various programming languages, including Python, JavaScript, and C++.
3. Factual Integrity and Precision: Trained on curated and aligned datasets to enhance accuracy and reduce hallucination in fact-based tasks.
4. Long-Context Support: Capable of handling up to 128K tokens as input with output generation up to 8K tokens, enabling detailed and comprehensive responses over extended sequences.
5. Instruction-Tuned Alignment: Demonstrates a strong ability to follow multi-step instructions, maintain conversation context, and produce structured outputs across sessions.
6. Multilingual Proficiency: Supports over 29 languages including English, Chinese, French, Spanish, Arabic, Russian, Japanese, Korean, and others, enabling global communication and translation tasks.

📚 Documentation

Intended Use

• Mathematical and symbolic problem solving
• Code generation and explanation
• Structured response generation in JSON, Markdown, or table formats
• Long-form technical writing and documentation
• Factual question answering and fact-checking
• Educational assistance across STEM domains
• Multilingual conversation and translation tasks

Limitations

• High computational requirements (A100/H100-class GPUs recommended)
• May still produce hallucinated facts on edge cases or adversarial inputs
• Sensitive to poorly structured or ambiguous prompts
• Early-stage errors may propagate in long outputs
• Less suitable for creative fiction or subjective narrative tasks

📄 License

This project is licensed under the Apache-2.0 license.

🔗 References

1. Analysing Mathematical Reasoning Abilities of Neural Models. arXiv:1904.01557. https://arxiv.org/pdf/1904.01557
2. YaRN: Efficient Context Window Extension of Large Language Models. arXiv:2309.00071. https://arxiv.org/pdf/2309.00071

📋 Information Table