---
license: llama3
language:
- en
- ja
- zh
base_model:
- meta-llama/Meta-Llama-3-8B
pipeline_tag: text-generation
library_name: transformers
---
# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

|                          | EN        |       |       |         |          |
|--------------------------|-----------|-------|-------|---------|----------|
| Model                    | MedQA-4op | MedQA | MMLU  | MedMCQA | PubMedQA |
| Gemma -7B                | 52.92     | 47.56 | 69.74 | 48.67   | 73.44    |
| Llama2 -7B               | 36.59     | 28.79 | 44.19 | 36.27   | 32.80    |
| Llama3 -8B               | 58.52     | 52.76 | 70.02 | 55.25   | 75.05    |
| Swallow -8B -v0.1        | 47.87     | 45.66 | 65.87 | 49.99   | 64.39    |
| med alpaca -7B           | 37.62     | 30.99 | 51.75 | 34.23   | 39.84    |
| Meditron -7B             | 35.09     | 29.10 | 46.96 | 29.88   | 20.52    |
| Open BioLLM -8B          | 40.14     | 50.08 | 73.15 | 56.23   | 65.39    |
| DISC -MedLLM             | 37.46     | 32.89 | 50.00 | 36.96   | 33.20    |
| Apollo -7B               | 54.97     | 49.68 | 68.73 | 53.48   | 75.86    |
| ELAINE -medLLM           | 56.15     | 50.39 | 67.62 | 53.74   | 71.83    |
| ELAINE -medLLM -instruct | 58.36     | 55.84 | 72.79 | 54.48   | 73.24    |


|

|                          | ZH        |       |        | JA      |         |       |
|--------------------------|-----------|-------|--------|---------|---------|-------|
| Model                    | MedQA-4op | MedQA | CMExam | JJSIMQA | IgakuQA | DenQA |
| Gemma -7B                | 48.90     | 44.55 | 38.60  | 27.61   | 35.80   | 25.14 |
| Llama2 -7B               | 29.52     | 24.85 | 23.55  | 12.61   | 17.45   | 17.08 |
| Llama3 -8B               | 51.42     | 44.64 | 39.41  | 28.91   | 33.20   | 23.47 |
| Swallow -8B -v0.1        | 47.35     | 40.84 | 35.94  | 37.83   | 45.15   | 29.03 |
| med alpaca -7B           | 30.81     | 25.17 | 23.40  | 14.35   | 16.55   | 10.83 |
| Meditron -7B             | 31.10     | 24.47 | 22.61  | 13.48   | 18.15   | 15.56 |
| Open BioLLM -8B          | 50.37     | 42.59 | 24.59  | 20.87   | 31.50   | 14.44 |
| DISC -MedLLM             | 47.18     | 46.13 | 41.57  | 23.26   | 27.15   | 23.47 |
| Apollo -7B               | 65.19     | 60.98 | 51.40  | 25.00   | 37.40   | 24.72 |
| ELAINE -medLLM           | 57.50     | 52.44 | 44.99  | 35.65   | 45.75   | 29.86 |
| ELAINE -medLLM -instruct | 61.59     | 55.71 | 47.19  | 35.22   | 46.35   | 32.36 |





#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

[More Information Needed]

#### Hardware

[More Information Needed]

#### Software

[More Information Needed]

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

## Usage

```python

import string, time
from vllm import LLM, SamplingParams
import torch

model_name = "kenyano/ELAINE_medLLM"

vllm_paralell = 1

questions_ja = [
    "尿酸値の値はどこまでが正常値ですか？",
]

questions_en = [
    "What is the normal level of uric acid levels?" ,
]

questions_zh = [
    "尿酸的正常水平是多少？",
]


llm = LLM(model=model_name,
            trust_remote_code=True,
            tensor_parallel_size=vllm_paralell,
            dtype="half",
            max_model_len=8192)

sampling_params = SamplingParams(temperature=0.2, top_p=0.8, max_tokens=200, min_tokens=50)

def generate(questions):

    prompts = [f"Human: \n{question}\n\nAssistant: \n" for question in questions]
    outputs = llm.generate(prompts,sampling_params)

    for i, output in enumerate(outputs):
        prompt = output.prompt
        generated_text = output.outputs[0].text

        print("-"*5, "prompt", "-"*5)
        print(f'{prompt}')
        print("-"*5, "generaated", "-"*5)
        print(f'{generated_text}\n')


generate(questions_ja)
generate(questions_en)
generate(questions_zh)

```