tchebonenko
commited on
Commit
•
1d939da
1
Parent(s):
f2c7664
fix
Browse files
README.md
CHANGED
@@ -1,11 +1,14 @@
|
|
1 |
-
#
|
|
|
|
|
|
|
|
|
2 |
Using a transcript of a patient visit with his/her general health care provider (GP) recommend where that patient should be referred to and extract the main keywords from the transcript.
|
3 |
<br>
|
4 |
For example, if a patient has allergy-related concerns, then GP needs to refer that patient to the allergy/immunology department or an immunology doctor available.
|
5 |
<br><br>
|
6 |
Extracted keywords are there to help the doctor in making the final decision of what to recommend to the patient.
|
7 |
-
<br><br
|
8 |
-
The model is a BLOOMZ-based medical model created using peft, transformers, and bitsandbytes.
|
9 |
|
10 |
---
|
11 |
**dataset for fine-tuning:**
|
|
|
1 |
+
# Fine-tuned BLOOMZ medical
|
2 |
+
The model is based on [BLOOMZ-3B](https://huggingface.co/bigscience/bloomz) a large language model trained by the BigScience team. <br>
|
3 |
+
The full paper is available [here](https://arxiv.org/abs/2211.01786).<br>
|
4 |
+
The model is a created using peft, transformers, and bitsandbytes.
|
5 |
+
#The goal of the model
|
6 |
Using a transcript of a patient visit with his/her general health care provider (GP) recommend where that patient should be referred to and extract the main keywords from the transcript.
|
7 |
<br>
|
8 |
For example, if a patient has allergy-related concerns, then GP needs to refer that patient to the allergy/immunology department or an immunology doctor available.
|
9 |
<br><br>
|
10 |
Extracted keywords are there to help the doctor in making the final decision of what to recommend to the patient.
|
11 |
+
<br><br>
|
|
|
12 |
|
13 |
---
|
14 |
**dataset for fine-tuning:**
|