grimjim/llama-3-aaditya-OpenBioLLM-8B

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kLicense:llama3Architecture:Transformer Warm

grimjim/llama-3-aaditya-OpenBioLLM-8B is an 8 billion parameter language model developed by Saama AI Labs, fine-tuned from Meta-Llama-3-8B. It is specifically designed for the biomedical domain, leveraging a custom medical instruction dataset and Direct Preference Optimization. This model excels at biomedical tasks such as clinical note summarization, medical question answering, and clinical entity recognition, demonstrating superior performance compared to other open-source models of similar scale.

Loading preview...

OpenBioLLM-8B: A Specialized Biomedical LLM

OpenBioLLM-8B, developed by Saama AI Labs, is an 8 billion parameter language model built upon the Meta-Llama-3-8B architecture. It is meticulously fine-tuned for the biomedical domain, utilizing a vast corpus of high-quality biomedical data and advanced training techniques including Direct Preference Optimization (DPO) with the Nectar ranking dataset and a custom medical instruction dataset.

Key Capabilities

  • Biomedical Specialization: Tailored for medical and life sciences, understanding and generating domain-specific text with high accuracy.
  • Superior Performance: Outperforms other open-source biomedical models of similar scale and shows better results than larger proprietary models like GPT-3.5 and Meditron-70B on various biomedical benchmarks.
  • Clinical Note Summarization: Efficiently analyzes and summarizes complex clinical notes, EHR data, and discharge summaries.
  • Medical Question Answering: Provides answers to a wide range of medical questions.
  • Clinical Entity Recognition: Identifies and extracts key medical concepts (diseases, symptoms, medications, procedures) from unstructured clinical text.
  • Biomarker Extraction: Capable of extracting biomarkers from text.
  • Classification: Performs biomedical classification tasks such as disease prediction and medical document categorization.
  • De-Identification: Detects and removes Personally Identifiable Information (PII) from medical records for privacy compliance.

Good for

  • Researchers and developers in healthcare and life sciences.
  • Applications requiring accurate understanding and generation of biomedical text.
  • Tasks like clinical decision support, pharmacovigilance, and medical research (with appropriate validation and human oversight).

Advisory: This model is intended for research and development only and should not be used for direct patient care or clinical decision-making without rigorous evaluation and validation.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p