JSL-MedPhi2-2.7B
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 info@johnsnowlabs.com.
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "johnsnowlabs/JSL-MedPhi2-2.7B"
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"])
π Evaluation
Tasks | Version | Filter | n-shot | Metric | Value | Stderr | |
---|---|---|---|---|---|---|---|
stem | N/A | none | 0 | acc_norm | 0.3904 | Β± | 0.0066 |
none | 0 | acc | 0.4402 | Β± | 0.0058 | ||
- medmcqa | Yaml | none | 0 | acc | 0.3899 | Β± | 0.0075 |
none | 0 | acc_norm | 0.3899 | Β± | 0.0075 | ||
- medqa_4options | Yaml | none | 0 | acc | 0.3920 | Β± | 0.0137 |
none | 0 | acc_norm | 0.3920 | Β± | 0.0137 | ||
- anatomy (mmlu) | 0 | none | 0 | acc | 0.4815 | Β± | 0.0432 |
- clinical_knowledge (mmlu) | 0 | none | 0 | acc | 0.6340 | Β± | 0.0296 |
- college_biology (mmlu) | 0 | none | 0 | acc | 0.6181 | Β± | 0.0406 |
- college_medicine (mmlu) | 0 | none | 0 | acc | 0.5665 | Β± | 0.0378 |
- medical_genetics (mmlu) | 0 | none | 0 | acc | 0.6300 | Β± | 0.0485 |
- professional_medicine (mmlu) | 0 | none | 0 | acc | 0.4522 | Β± | 0.0302 |
- pubmedqa | 1 | none | 0 | acc | 0.7300 | Β± | 0.0199 |
Groups | Version | Filter | n-shot | Metric | Value | Stderr | |
---|---|---|---|---|---|---|---|
stem | N/A | none | 0 | acc_norm | 0.3904 | Β± | 0.0066 |
none | 0 | acc | 0.4402 | Β± | 0.0058 |
- Downloads last month
- 2,622
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.