aaditya commited on
Commit
1e2e1e1
·
verified ·
1 Parent(s): c5c5459

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -216,7 +216,7 @@ print(outputs[0]["generated_text"][len(prompt):])
216
 
217
  # Benchmark Results
218
 
219
- 🔥 OpenBioMed-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Gemini, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
220
 
221
  🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
222
 
@@ -246,19 +246,19 @@ print(outputs[0]["generated_text"][len(prompt):])
246
 
247
  # Use Cases & Examples
248
 
249
- 🚨 **Below results are from the quantized version of OpenBioMed-70B**
250
 
251
 
252
  # Summarize Clinical Notes
253
 
254
- OpenBioMed-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
255
 
256
 
257
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png)
258
 
259
  # Answer Medical Questions
260
 
261
- OpenBioMed-70B can provide answers to a wide range of medical questions.
262
 
263
 
264
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png)
@@ -276,7 +276,7 @@ OpenBioMed-70B can provide answers to a wide range of medical questions.
276
 
277
  # Clinical Entity Recognition
278
 
279
- OpenBioMed-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
280
 
281
 
282
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png)
@@ -291,13 +291,13 @@ OpenBioMed-70B can perform advanced clinical entity recognition by identifying a
291
 
292
  # Classification
293
 
294
- OpenBioMed-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
295
 
296
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png)
297
 
298
  # De-Identification
299
 
300
- OpenBioMed-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
301
 
302
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png)
303
 
 
216
 
217
  # Benchmark Results
218
 
219
+ 🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Gemini, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
220
 
221
  🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
222
 
 
246
 
247
  # Use Cases & Examples
248
 
249
+ 🚨 **Below results are from the quantized version of OpenBioLLM-70B**
250
 
251
 
252
  # Summarize Clinical Notes
253
 
254
+ OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
255
 
256
 
257
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png)
258
 
259
  # Answer Medical Questions
260
 
261
+ OpenBioLLM-70B can provide answers to a wide range of medical questions.
262
 
263
 
264
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png)
 
276
 
277
  # Clinical Entity Recognition
278
 
279
+ OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
280
 
281
 
282
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png)
 
291
 
292
  # Classification
293
 
294
+ OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
295
 
296
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png)
297
 
298
  # De-Identification
299
 
300
+ OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
301
 
302
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png)
303