You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am Sobjanta created by Excite Ai Limited And TechKnowGram Limited
31
+
defpaint(self, painter, option, widget):
32
+
painter.setPen(QColor(0, 0, 0)) # Use QColor to set the pen color
33
+
painter.setBrush(QBrush(self.baseColor))
34
+
painter.drawPath(self.shape())
31
35
32
-
input: Who developed you?
33
-
Excite Ai Limited And TechKnowGram Limited
34
-
35
-
input: President of Bangladesh?
36
-
President of Bangladesh is Mohammad Sahabuddin.
37
-
38
-
input: ICT minister of Bangladesh?
39
-
ICT minister of Bangladesh is Junayed Ahmed Palak
40
-
41
-
"""
42
-
43
-
response=model.predict(
44
-
input_template+content,
45
-
temperature=temperature,
46
-
max_output_tokens=max_decode_steps,
47
-
top_k=top_k,
48
-
top_p=top_p,
49
-
)
50
-
# choices = response.choices
51
-
# choice_list = [choice.get("text").lstrip("\n") for choice in choices]
52
-
print(response)
53
-
returnresponse
54
-
palm=lambdaprompt: get_response(
55
-
"stoked-brand-391605",
56
-
"text-bison", # "text-bison@001" ... without versioning, it's the "latest"
57
-
0.5, # rather low temperature, can go up to 1. default 0.2, changing to 0.5 just to see what happens
58
-
512, # number of tokens, default 256, setting to 512
59
-
0.8, # top-p: most probable? no clue what this is. Top-p changes how the model selects tokens for output. Tokens are selected from most probable to least until the sum of their probabilities equals the top-p value. For example, if tokens A, B, and C have a probability of .3, .2, and .1 and the top-p value is .5, then the model will select either A or B as the next token (using temperature). The default top-p value is .8.
60
-
40, # top-k for next token. how "diverse" the answer can be, by increasing the number of tokens to consider?
0 commit comments