AeroxLabs/Aerova-Nova-2.5B-GGUF overview

---

license: mit

datasets:

- ncbi/pubmed

language:

- en

- es

- de

- pt

- ru

- fr

- ar

- zh

base_model:

- BioMistral/BioMistral-7B-SLERP

pipeline_tag: text-generation

library_name: transformers

tags:

- medical

- biology

- biomedical

- text-generation

- gguf

- llama-cpp

- llama-cpp-python

- 7b

---

!Aerova

---

<h1 align="center">Aerova Nova</h1>

Medical intelligence, built for biomedical language.

Aerova Nova is a 7B-parameter biomedical language model developed by AeroxLabs, designed for medical, biological, and scientific text generation.

Built on BioMistral/BioMistral-7B-SLERP and trained with biomedical data from PubMed, Nova explores how open-source language models can be adapted toward specialized medical knowledge.

Nova is designed for research, experimentation, education, and biomedical NLP applications.

---

Model Overview

| | |

| ----------------- | ---------------------------- |

| Model | Aerova Nova |

| Parameters | 7B |

| Architecture | Causal Language Model |

| Base Model | BioMistral-7B-SLERP |

| Domain | Medicine & Biology |

| Languages | 8 |

| Training Data | NCBI PubMed |

| Format | GGUF |

| Inference | llama.cpp / llama-cpp-python |

| License | MIT |

---

What Nova Can Do

Nova is designed for biomedical language tasks including:

• Medical and biological text generation
• Biomedical question answering
• Scientific text completion
• Medical knowledge exploration
• Biomedical NLP research
• Educational experimentation
• Domain-specific language generation

Nova focuses on specialized biomedical language rather than general-purpose conversational intelligence.

---

Training

Nova builds upon BioMistral-7B-SLERP, adapting a strong open-source language model toward biomedical and medical language.

The primary dataset used in development is NCBI PubMed, providing large-scale biomedical literature for domain-specific language modeling.

Base model: BioMistral/BioMistral-7B-SLERP

Dataset: NCBI PubMed

---

Supported Languages

Nova's training configuration includes:

• English
• Spanish
• German
• Portuguese
• Russian
• French
• Arabic
• Chinese

Performance may vary between languages, particularly when working with specialized biomedical terminology.

---

Running Nova

Nova is distributed in GGUF format and is designed for efficient local inference with the llama.cpp ecosystem.

llama-cpp-python

Install the Python bindings:

pip install llama-cpp-python

Then load the model:

from llama_cpp import Llama

llm = Llama(
    model_path="./Aerova-Nova.gguf",
    n_ctx=4096,
    verbose=False,
)

output = llm(
    "Explain the role of hemoglobin in oxygen transport.",
    max_tokens=256,
    temperature=0.7,
)

print(output["choices"][0]["text"])

For compatible GPUs, layers can be offloaded with:

llm = Llama(
    model_path="./Aerova-Nova.gguf",
    n_ctx=4096,
    n_gpu_layers=-1,
)

For more advanced inference options, refer to the llama-cpp-python documentation.

---

Intended Use

Nova is intended for:

• Biomedical research
• Natural language processing research
• Educational projects
• Medical AI experimentation
• Scientific text generation
• Prototyping domain-specific AI systems
• Local and private model inference

Nova can also serve as a foundation for further research and fine-tuning on specialized biomedical tasks.

---

Limitations & Safety

Nova is a research model and its outputs should be treated as generated information rather than authoritative medical advice.

The model may produce:

• Incorrect or incomplete information
• Hallucinated medical facts
• Outdated information
• Biased responses
• Overconfident statements
• Incorrect interpretations of scientific literature

Nova should not be used as a substitute for qualified medical professionals or as the sole basis for diagnosis, treatment, or other clinical decisions.

Always verify medical information using appropriate authoritative sources and qualified professionals.

---

Open Source

Aerova Nova is released openly so researchers, developers, and students can experiment with biomedical language models and build upon the work.

Open models make it possible to study specialized AI systems, reproduce experiments, and develop new applications without relying entirely on closed systems.

Nova is part of Aerova's open model research.

---

Credits

Developor: Vihaan Mody

Base model: BioMistral/BioMistral-7B-SLERP

Dataset: NCBI PubMed

Inference: llama.cpp / llama-cpp-python

---

License

Aerova Nova is released under the MIT License.

See LICENSE for the full license text.

---

<div align="center">

AeroxLabs

Advancing Medicine with Artifical Intelligence.

</div>