JSL-MedMNX-7B-SFT

JSL-MedMNX-7B-SFT is a 7 Billion parameter model developed by John Snow Labs.

This model is SFT-finetuned on alpaca format 11k medical dataset over the base model JSL-MedMNX-7B. Checkout the perofrmance on Open Medical LLM Leaderboard.

This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at info@johnsnowlabs.com.

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "johnsnowlabs/JSL-MedMNX-7B-SFT"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

πŸ† Evaluation

Tasks Version Filter n-shot Metric Value Stderr
stem N/A none 0 acc_norm 0.5209 Β± 0.0068
none 0 acc 0.5675 Β± 0.0058
- medmcqa Yaml none 0 acc 0.5152 Β± 0.0077
none 0 acc_norm 0.5152 Β± 0.0077
- medqa_4options Yaml none 0 acc 0.5397 Β± 0.0140
none 0 acc_norm 0.5397 Β± 0.0140
- anatomy (mmlu) 0 none 0 acc 0.6593 Β± 0.0409
- clinical_knowledge (mmlu) 0 none 0 acc 0.7245 Β± 0.0275
- college_biology (mmlu) 0 none 0 acc 0.7431 Β± 0.0365
- college_medicine (mmlu) 0 none 0 acc 0.6532 Β± 0.0363
- medical_genetics (mmlu) 0 none 0 acc 0.7300 Β± 0.0446
- professional_medicine (mmlu) 0 none 0 acc 0.7206 Β± 0.0273
- pubmedqa 1 none 0 acc 0.7720 Β± 0.0188
Groups Version Filter n-shot Metric Value Stderr
stem N/A none 0 acc_norm 0.5209 Β± 0.0068
none 0 acc 0.5675 Β± 0.0058
Downloads last month
2,867
Safetensors
Model size
7.24B params
Tensor type
FP16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for johnsnowlabs/JSL-MedMNX-7B-SFT

Quantizations
1 model