README.md

metadata

base_model:
  - ruslanmv/ai-medical-model-32bit
  - Locutusque/Llama-3-Hercules-5.0-8B
  - refuelai/Llama-3-Refueled
library_name: transformers
tags:
  - mergekit
  - merge

merge

This is a merge of pre-trained language models created using mergekit.

This model is effective in structuring the unstructured clinical texts.

Model Composition and Features:

1. Base Model: The foundation of Sethu's model is based on "refuelai/Llama-3-Refueled," which itself is a refined version of the Llama3-8B model, renowned for its instruction-following capabilities and adaptability across various domains.

2. Merged Models:

   • ruslanmv/ai-medical-model-32bit: A model fine-tuned specifically for answering technical medical questions, providing a solid base of medical knowledge.
   • Locutusque/Llama-3-Hercules-5.0-8B: Known for its ability to follow complex instructions and handle conversational interactions effectively, especially in scientific and technical contexts.

This model was merged using the DARE TIES merge method using refuelai/Llama-3-Refueled as a base.

Models Merged

The following models were included in the merge:

• ruslanmv/ai-medical-model-32bit
• Locutusque/Llama-3-Hercules-5.0-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Locutusque/Llama-3-Hercules-5.0-8B
    parameters:
      weight: [0.25, 0.35, 0.45, 0.35, 0.25]
      density: [0.1, 0.25, 0.5, 0.25, 0.1]
  - model: refuelai/Llama-3-Refueled
  - model: ruslanmv/ai-medical-model-32bit
    parameters:
      weight: [0.55, 0.45, 0.35, 0.45, 0.55]
      density: [0.1, 0.25, 0.5, 0.25, 0.1]
merge_method: dare_ties
base_model: refuelai/Llama-3-Refueled
parameters:
  int8_mask: true
dtype: bfloat16

<|begin_of_text|><|start_header_id|>user<|end_header_id|>

A 52-year-old woman comes to the physician because of a 6-month history of generalized fatigue, low-grade fever, and a 10-kg (22-lb) weight loss. Physical examination shows generalized pallor and splenomegaly. Her hemoglobin concentration is 7.5 g/dL and leukocyte count is 41,800/mm3. Leukocyte alkaline phosphatase activity is low. Peripheral blood smear shows basophilia with myelocytes and metamyelocytes. Bone marrow biopsy shows cellular hyperplasia with proliferation of immature granulocytic cells. Which of the following mechanisms is most likely responsible for this patient's condition?
    Output JSON in this format.
    {
    "age":
    "gender"
    "past medicial history"
    "present symptoms"
    "interventions"
    "lab tests"
    "medications"
    "possible diseases"
    }
    
    PLEASE WRITE ONLY JSON<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{
    "age": 52,
    "gender": "female",
    "past medical history": null,
    "present symptoms": ["generalized fatigue", "low-grade fever", "10-kg (22-lb) weight loss"],
    "interventions": null,
    "lab tests": ["hemoglobin concentration: 7.5 g/dL", "leukocyte count: 41,800/mm3", "leukocyte alkaline phosphatase activity: low", "peripheral blood smear: basophilia with myelocytes and metamyelocytes", "bone marrow biopsy: cellular hyperplasia with proliferation of immature granulocytic cells"],
    "medications": null,
    "possible diseases": ["chronic myeloid leukemia"]
}<|eot_id|><|end_of_text|>

Limitations and Ethical Considerations:

• Reliance on Training Data: The model's effectiveness is contingent on the diversity and quality of the data it was trained on. There could be limitations in scenarios where it encounters rare or atypical medical cases not well-represented in the training data.
• Potential Bias: As with any AI model, there is a risk of bias inherent in the training datasets, which could influence the responses in unforeseen ways.
• Use as a Supplement, Not a Replacement: It is crucial to note that while this model can provide valuable assistance, it should not replace consultation with qualified medical professionals.