Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ tags:
|
|
12 |
- biology
|
13 |
---
|
14 |
# Model Card for Model ID
|
15 |
-
|
16 |
## How to use
|
17 |
|
18 |
Loading the model from Hunggingface:
|
@@ -61,9 +61,20 @@ with torch.no_grad():
|
|
61 |
answer = tokenizer.decode(output[0], skip_special_tokens=True)
|
62 |
print(answer)
|
63 |
```
|
64 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
|
66 |
-
|
67 |
|
|
|
68 |
|
69 |
|
|
|
12 |
- biology
|
13 |
---
|
14 |
# Model Card for Model ID
|
15 |
+
More code details can be found at Github: https://github.com/Incredible88/BioMistral-Clinical-7B
|
16 |
## How to use
|
17 |
|
18 |
Loading the model from Hunggingface:
|
|
|
61 |
answer = tokenizer.decode(output[0], skip_special_tokens=True)
|
62 |
print(answer)
|
63 |
```
|
64 |
+
## Incremental learning
|
65 |
+
The process of incremental learning:
|
66 |
+

|
67 |
+
The training process records:
|
68 |
+

|
69 |
+
|
70 |
+
## Clinical Scenario Analysis
|
71 |
+
More informative answer than BioMistral-7B:
|
72 |
+

|
73 |
+
|
74 |
+
## Supervised Fine-tuning Benchmark
|
75 |
|
76 |
+

|
77 |
|
78 |
+
**CAUTION!** Both direct and downstream users need to be informed about the risks, biases, and constraints inherent in the model. While the model can produce natural language text, our exploration of its capabilities and limitations is just beginning. In fields such as medicine, comprehending these limitations is crucial. Hence, we strongly advise against deploying this model for natural language generation in production or for professional tasks in the realm of health and medicine.
|
79 |
|
80 |
|