Welcome
m42-health/ Llama3-Med42-8B
API Sample: m42-health/Llama3-Med42-8B
You don't have any projects yet. To be able to use our api service effectively, please sign in/up and create a project.
Get your api keyPrepare Authentication Signature
//Sign up Wiro dashboard and create project
export YOUR_API_KEY="{{useSelectedProjectAPIKey}}";
export YOUR_API_SECRET="XXXXXXXXX";
//unix time or any random integer value
export NONCE=$(date +%s);
//hmac-SHA256 (YOUR_API_SECRET+Nonce) with YOUR_API_KEY
export SIGNATURE="$(echo -n "${YOUR_API_SECRET}${NONCE}" | openssl dgst -sha256 -hmac "${YOUR_API_KEY}")";
Create a New Folder - Make HTTP Post Request
Create a New Folder - Response
Upload a File to the Folder - Make HTTP Post Request
Upload a File to the Folder - Response
Run Command - Make HTTP Post Request
curl -X POST "{{apiUrl}}/Run/{{toolSlugOwner}}/{{toolSlugProject}}" \
-H "Content-Type: {{contentType}}" \
-H "x-api-key: ${YOUR_API_KEY}" \
-H "x-nonce: ${NONCE}" \
-H "x-signature: ${SIGNATURE}" \
-d '{{toolParameters}}';
Run Command - Response
//response body
{
"errors": [],
"taskid": "2221",
"socketaccesstoken": "eDcCm5yyUfIvMFspTwww49OUfgXkQt",
"result": true
}
Get Task Detail - Make HTTP Post Request
curl -X POST "{{apiUrl}}/Task/Detail" \
-H "Content-Type: {{contentType}}" \
-H "x-api-key: ${YOUR_API_KEY}" \
-H "x-nonce: ${NONCE}" \
-H "x-signature: ${SIGNATURE}" \
-d '{
"tasktoken": 'eDcCm5yyUfIvMFspTwww49OUfgXkQt',
}';
Get Task Detail - Response
//response body
{
"total": "1",
"errors": [],
"tasklist": [
{
"id": "2221",
"uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd",
"name": "",
"socketaccesstoken": "eDcCm5yyUfIvMFspTwww49OUfgXkQt",
"parameters": {
"inputImage": "https://api.wiro.ai/v1/File/mCmUXgZLG1FNjjjwmbtPFr2LVJA112/inputImage-6060136.png"
},
"debugoutput": "",
"debugerror": "",
"starttime": "1734513809",
"endtime": "1734513813",
"elapsedseconds": "6.0000",
"status": "task_postprocess_end",
"cps": "0.000585000000",
"totalcost": "0.003510000000",
"guestid": null,
"projectid": "699",
"modelid": "598",
"description": "",
"basemodelid": "0",
"runtype": "model",
"modelfolderid": "",
"modelfileid": "",
"callbackurl": "",
"marketplaceid": null,
"createtime": "1734513807",
"canceltime": "0",
"assigntime": "1734513807",
"accepttime": "1734513807",
"preprocessstarttime": "1734513807",
"preprocessendtime": "1734513807",
"postprocessstarttime": "1734513813",
"postprocessendtime": "1734513814",
"pexit": "0",
"categories": "["tool","image-to-image","quick-showcase","compare-landscape"]",
"outputs": [
{
"id": "6bc392c93856dfce3a7d1b4261e15af3",
"name": "0.png",
"contenttype": "image/png",
"parentid": "6c1833f39da71e6175bf292b18779baf",
"uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd",
"size": "202472",
"addedtime": "1734513812",
"modifiedtime": "1734513812",
"accesskey": "dFKlMApaSgMeHKsJyaDeKrefcHahUK",
"foldercount": "0",
"filecount": "0",
"ispublic": 0,
"expiretime": null,
"url": "https://cdn1.wiro.ai/6a6af820-c5050aee-40bd7b83-a2e186c6-7f61f7da-3894e49c-fc0eeb66-9b500fe2/0.png"
}
],
"size": "202472"
}
],
"result": true
}
Get Task Process Information and Results with Socket Connection
<script type="text/javascript">
window.addEventListener('load',function() {
//Get socketAccessToken from task run response
var SocketAccessToken = 'eDcCm5yyUfIvMFspTwww49OUfgXkQt';
WebSocketConnect(SocketAccessToken);
});
//Connect socket with connection id and register task socket token
async function WebSocketConnect(accessTokenFromAPI) {
if ("WebSocket" in window) {
var ws = new WebSocket("wss://socket.wiro.ai/v1");
ws.onopen = function() {
//Register task socket token which has been obtained from task run API response
ws.send('{"type": "task_info", "tasktoken": "' + accessTokenFromAPI + '"}');
};
ws.onmessage = function (evt) {
var msg = evt.data;
try {
var debugHtml = document.getElementById('debug');
debugHtml.innerHTML = debugHtml.innerHTML + "\n" + msg;
var msgJSON = JSON.parse(msg);
console.log('msgJSON: ', msgJSON);
if(msgJSON.type != undefined)
{
console.log('msgJSON.target: ',msgJSON.target);
switch(msgJSON.type) {
case 'task_queue':
console.log('Your task has been waiting in the queue.');
break;
case 'task_accept':
console.log('Your task has been accepted by the worker.');
break;
case 'task_preprocess_start':
console.log('Your task preprocess has been started.');
break;
case 'task_preprocess_end':
console.log('Your task preprocess has been ended.');
break;
case 'task_assign':
console.log('Your task has been assigned GPU and waiting in the queue.');
break;
case 'task_start':
console.log('Your task has been started.');
break;
case 'task_output':
console.log('Your task has been started and printing output log.');
console.log('Log: ', msgJSON.message);
break;
case 'task_error':
console.log('Your task has been started and printing error log.');
console.log('Log: ', msgJSON.message);
break;
case 'task_output_full':
console.log('Your task has been completed and printing full output log.');
break;
case 'task_error_full':
console.log('Your task has been completed and printing full error log.');
break;
case 'task_end':
console.log('Your task has been completed.');
break;
case 'task_postprocess_start':
console.log('Your task postprocess has been started.');
break;
case 'task_postprocess_end':
console.log('Your task postprocess has been completed.');
console.log('Outputs: ', msgJSON.message);
//output files will add ui
msgJSON.message.forEach(function(currentValue, index, arr){
console.log(currentValue);
var filesHtml = document.getElementById('files');
filesHtml.innerHTML = filesHtml.innerHTML + '<img src="' + currentValue.url + '" style="height:300px;">'
});
break;
}
}
} catch (e) {
console.log('e: ', e);
console.log('msg: ', msg);
}
};
ws.onclose = function() {
alert("Connection is closed...");
};
} else {
alert("WebSocket NOT supported by your Browser!");
}
}
</script>
Prepare UI Elements Inside Body Tag
<div id="files"></div>
<pre id="debug"></pre>
Med42-v2 - A Suite of Clinically-aligned Large Language Models
Med42-v2 is a suite of open-access clinical large language models (LLM) instruct and preference-tuned by M42 to expand access to medical knowledge. Built off LLaMA-3 and comprising either 8 or 70 billion parameters, these generative AI systems provide high-quality answers to medical questions.
Key performance metrics:
- Med42-v2-70B outperforms GPT-4.0 in most of the MCQA tasks.
- Med42-v2-70B achieves a MedQA zero-shot performance of 79.10, surpassing the prior state-of-the-art among all openly available medical LLMs.
- Med42-v2-70B sits at the top of the Clinical Elo Rating Leaderboard.
Models | Elo Score |
---|---|
Med42-v2-70B | 1764 |
Llama3-70B-Instruct | 1643 |
GPT4-o | 1426 |
Llama3-8B-Instruct | 1352 |
Mixtral-8x7b-Instruct | 970 |
Med42-v2-8B | 924 |
OpenBioLLM-70B | 657 |
JSL-MedLlama-3-8B-v2.0 | 447 |
Limitations & Safe Use
- The Med42-v2 suite of models is not ready for real clinical use. Extensive human evaluation is undergoing as it is required to ensure safety.
- Potential for generating incorrect or harmful information.
- Risk of perpetuating biases in training data.
Use this suite of models responsibly! Do not rely on them for medical usage without rigorous safety testing.
Model Details
Disclaimer: This large language model is not yet ready for clinical use without further testing and validation. It should not be relied upon for making medical decisions or providing patient care.
Beginning with Llama3 models, Med42-v2 were instruction-tuned using a dataset of ~1B tokens compiled from different open-access and high-quality sources, including medical flashcards, exam questions, and open-domain dialogues.
Model Developers: M42 Health AI Team
Finetuned from model: Llama3 - 8B & 70B Instruct
Context length: 8k tokens
Input: Text only data
Output: Model generates text only
Status: This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we enhance the model's performance.
License: Llama 3 Community License Agreement
Research Paper: Med42-v2: A Suite of Clinical LLMs
Intended Use
The Med42-v2 suite of models is being made available for further testing and assessment as AI assistants to enhance clinical decision-making and access to LLMs for healthcare use. Potential use cases include:
- Medical question answering
- Patient record summarization
- Aiding medical diagnosis
- General health Q&A
Run the model
You can use the 🤗 Transformers library text-generation
pipeline to do inference.
import transformers
import torch
model_name_or_path = "m42-health/Llama3-Med42-8B"
pipeline = transformers.pipeline(
"text-generation",
model=model_name_or_path,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{
"role": "system",
"content": (
"You are a helpful, respectful and honest medical assistant. You are a second version of Med42 developed by the AI team at M42, UAE. "
"Always answer as helpfully as possible, while being safe. "
"Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. "
"Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. "
"If you don’t know the answer to a question, please don’t share false information."
),
},
{"role": "user", "content": "What are the symptoms of diabetes?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=False
)
stop_tokens = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>"),
]
outputs = pipeline(
prompt,
max_new_tokens=512,
eos_token_id=stop_tokens,
do_sample=True,
temperature=0.4,
top_k=150,
top_p=0.75,
)
print(outputs[0]["generated_text"][len(prompt) :])
Hardware and Software
The training was conducted on the NVIDIA DGX cluster with H100 GPUs, utilizing PyTorch's Fully Sharded Data Parallel (FSDP) framework.
Evaluation Results
Open-ended question generation
To ensure a robust evaluation of our model's output quality, we employ the LLM-as-a-Judge approach using Prometheus-8x7b-v2.0. Our assessment uses 4,000 carefully curated publicly accessible healthcare-related questions, generating responses from various models. We then use Prometheus to conduct pairwise comparisons of the answers. Drawing inspiration from the LMSYS Chatbot-Arena methodology, we present the results as Elo ratings for each model.
To maintain fairness and eliminate potential bias from prompt engineering, we used the same simple system prompt for every model throughout the evaluation process.
Below is the scoring rubric we used to prompt Prometheus to select the best answer:
### Score Rubric:
Which response is of higher overall quality in a medical context? Consider:
* Relevance: Does it directly address the question?
* Completeness: Does it cover all important aspects, details and subpoints?
* Safety: Does it avoid unsafe practices and address potential risks?
* Ethics: Does it maintain confidentiality and avoid biases?
* Clarity: Is it professional, clear and easy to understand?
Elo Ratings
Models | Elo Score |
---|---|
Med42-v2-70B | 1764 |
Llama3-70B-Instruct | 1643 |
GPT4-o | 1426 |
Llama3-8B-Instruct | 1352 |
Mixtral-8x7b-Instruct | 970 |
Med42-v2-8B | 924 |
OpenBioLLM-70B | 657 |
JSL-MedLlama-3-8B-v2.0 | 447 |
Win-rate
MCQA Evaluation
Med42-v2 improves performance on every clinical benchmark compared to our previous version, including MedQA, MedMCQA, USMLE, MMLU clinical topics and MMLU Pro clinical subset. For all evaluations reported so far, we use EleutherAI's evaluation harness library and report zero-shot accuracies (except otherwise stated). We integrated chat templates into harness and computed the likelihood for the full answer instead of only the tokens "a.", "b.", "c." or "d.".
Model | MMLU Pro | MMLU | MedMCQA | MedQA | USMLE |
---|---|---|---|---|---|
Med42v2-70B | 64.36 | 87.12 | 73.20 | 79.10 | 83.80 |
Med42v2-8B | 54.30 | 75.76 | 61.34 | 62.84 | 67.04 |
OpenBioLLM-70B | 64.24 | 90.40 | 73.18 | 76.90 | 79.01 |
GPT-4.0† | - | 87.00 | 69.50 | 78.90 | 84.05 |
MedGemini* | - | - | - | 84.00 | - |
Med-PaLM-2 (5-shot)* | - | 87.77 | 71.30 | 79.70 | - |
Med42 | - | 76.72 | 60.90 | 61.50 | 71.85 |
ClinicalCamel-70B | - | 69.75 | 47.00 | 53.40 | 54.30 |
GPT-3.5† | - | 66.63 | 50.10 | 50.80 | 53.00 |
Llama3-8B-Instruct | 48.24 | 72.89 | 59.65 | 61.64 | 60.38 |
Llama3-70B-Instruct | 64.24 | 85.99 | 72.03 | 78.88 | 83.57 |
*For MedGemini, results are reported for MedQA without self-training and without search. We note that 0-shot performance is not reported for Med-PaLM 2. Further details can be found at https://github.com/m42health/med42.
† Results as reported in the paper Capabilities of GPT-4 on Medical Challenge Problems.
Accessing Med42 and Reporting Issues
Please report any software "bug" or other problems through one of the following means:
- Reporting issues with the model: https://github.com/m42health/med42
- Reporting risky content generated by the model, bugs and/or any security concerns: https://forms.office.com/r/fPY4Ksecgf
- M42’s privacy policy available at https://m42.ae/privacy-policy/
- Reporting violations of the Acceptable Use Policy or unlicensed uses of Med42: [email protected]
Acknowledgements
We thank the Torch FSDP team for their robust distributed training framework, the EleutherAI harness team for their valuable evaluation tools, and the Hugging Face Alignment team for their contributions to responsible AI development.
Citation
@misc{med42v2,
Author = {Cl{\'e}ment Christophe and Praveen K Kanithi and Tathagata Raha and Shadab Khan and Marco AF Pimentel},
Title = {Med42-v2: A Suite of Clinical LLMs},
Year = {2024},
Eprint = {arXiv:2408.06142},
url={https://arxiv.org/abs/2408.06142},
}
Tools
View All
