JSL-Med-Sft-Llama-3-8B

This model is developed by John Snow Labs.

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 [email protected].

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "johnsnowlabs/JSL-Med-Sft-Llama-3-8B"
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"])

🏆 Evaluation

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
stem	N/A	none	0	acc_norm	0.5803	±	0.0067
		none	0	acc	0.6141	±	0.0057
- medmcqa	Yaml	none	0	acc	0.5752	±	0.0076
		none	0	acc_norm	0.5752	±	0.0076
- medqa_4options	Yaml	none	0	acc	0.5970	±	0.0138
		none	0	acc_norm	0.5970	±	0.0138
- anatomy (mmlu)	0	none	0	acc	0.6963	±	0.0397
- clinical_knowledge (mmlu)	0	none	0	acc	0.7472	±	0.0267
- college_biology (mmlu)	0	none	0	acc	0.7847	±	0.0344
- college_medicine (mmlu)	0	none	0	acc	0.6185	±	0.0370
- medical_genetics (mmlu)	0	none	0	acc	0.8300	±	0.0378
- professional_medicine (mmlu)	0	none	0	acc	0.7022	±	0.0278
- pubmedqa	1	none	0	acc	0.7480	±	0.0194

Groups	Version	Filter	n-shot	Metric	Value		Stderr
stem	N/A	none	0	acc_norm	0.5803	±	0.0067
		none	0	acc	0.6141	±	0.0057