Update README.md
Browse filesAdd inference code sample
README.md
CHANGED
@@ -24,9 +24,26 @@ based on the information in their previous medical records, current symptoms, ag
|
|
24 |
|
25 |
## Intended uses & limitations ⁉️
|
26 |
|
27 |
-
|
28 |
```py
|
|
|
|
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
```
|
31 |
|
32 |
Uses: To use Artificial Intelligence technology to diagnose patient based off of multiple parameters ranging from their age to their
|
|
|
24 |
|
25 |
## Intended uses & limitations ⁉️
|
26 |
|
27 |
+
Code inference sample:
|
28 |
```py
|
29 |
+
from peft import PeftModel, PeftConfig
|
30 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
31 |
|
32 |
+
config = PeftConfig.from_pretrained("LaZeAsh/gemma-2b-lahacks")
|
33 |
+
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it")
|
34 |
+
model = PeftModel.from_pretrained(model, "LaZeAsh/gemma-2b-lahacks")
|
35 |
+
|
36 |
+
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
|
37 |
+
|
38 |
+
prompt = "I feel cold I most likely have a "
|
39 |
+
|
40 |
+
input_ids = tokenizer.encode(prompt, return_tensors = 'pt')
|
41 |
+
|
42 |
+
output = model.generate(input_ids, max_length=50, num_return_sequences=1)
|
43 |
+
|
44 |
+
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
45 |
+
|
46 |
+
print(generated_text)
|
47 |
```
|
48 |
|
49 |
Uses: To use Artificial Intelligence technology to diagnose patient based off of multiple parameters ranging from their age to their
|