Update README.md
Browse files
README.md
CHANGED
@@ -16,17 +16,11 @@ tags:
|
|
16 |
Based of the full weight llama 2-hermes from Nous Research.
|
17 |
|
18 |
### Model Description
|
19 |
-
|
20 |
-
<!-- This model was fine tuned off the full weight llama-2-hermes-7B from Nous Research. This model is a preemptive V1, and a hastily put together model to assist
|
21 |
in finance and compliance tasks, mostly tuned to the new SEC Marketing and Compliance rules established in 2021. Later iterations will have more guidelines and rulings
|
22 |
unrelated to the SEC Marketing rule.
|
23 |
https://www.sec.gov/files/rules/final/2020/ia-5653.pdf
|
24 |
-
|
25 |
-
Since the new marketing rule is principles based it requires logic, experience, and reasoning to determine if a statement or advertisement would be compliant within
|
26 |
-
the SEC's new guidelines. This can lead to multiple viewpoints of compliant or not depending on the viewer. Thus this is a small/high quality dataset version
|
27 |
-
to aid or provide an second viewpoint of a public facing statement to help determine if something is compliant per the SEC's guidelines. The dataset was crafted by
|
28 |
-
reviewing the SEC Marketing rule, other scenarios, and providing reasoning within the ###n\ Response n\### to help guide the model in reasoning tasks.
|
29 |
-
Further versions will be reviewed more for accuracy, bias, and more data. -->
|
30 |
|
31 |
|
32 |
|
@@ -47,9 +41,14 @@ Further versions will be reviewed more for accuracy, bias, and more data. -->
|
|
47 |
|
48 |
## Uses
|
49 |
|
50 |
-
|
51 |
-
|
52 |
-
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
### Direct Use
|
55 |
|
@@ -59,26 +58,33 @@ amongst other SEC rulings. -->
|
|
59 |
|
60 |
### Downstream Use [optional]
|
61 |
|
|
|
|
|
|
|
|
|
62 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
63 |
|
64 |
[More Information Needed]
|
65 |
|
66 |
### Out-of-Scope Use
|
67 |
|
|
|
|
|
68 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
69 |
|
70 |
[More Information Needed]
|
71 |
|
72 |
## Bias, Risks, and Limitations
|
73 |
|
|
|
|
|
74 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
75 |
|
76 |
[More Information Needed]
|
77 |
|
78 |
### Recommendations
|
79 |
|
80 |
-
<!--
|
81 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. -->
|
82 |
|
83 |
## How to Get Started with the Model
|
84 |
|
|
|
16 |
Based of the full weight llama 2-hermes from Nous Research.
|
17 |
|
18 |
### Model Description
|
19 |
+
This model was fine tuned off the full weight llama-2-hermes-7B from Nous Research. This model is a preemptive V1, and a hastily put together model to assist
|
|
|
20 |
in finance and compliance tasks, mostly tuned to the new SEC Marketing and Compliance rules established in 2021. Later iterations will have more guidelines and rulings
|
21 |
unrelated to the SEC Marketing rule.
|
22 |
https://www.sec.gov/files/rules/final/2020/ia-5653.pdf
|
23 |
+
<!-- -->
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
|
26 |
|
|
|
41 |
|
42 |
## Uses
|
43 |
|
44 |
+
This is to help companies and individuals within compliance and marketing departments to determine and find issues within their marketing or public facing documents.
|
45 |
+
Since the new marketing rule is principles based it requires logic, experience, and reasoning to determine if a statement or advertisement would be compliant within
|
46 |
+
the SEC's new guidelines. This can lead to multiple viewpoints of compliant or not depending on the viewer. Thus this is a small/high quality dataset version
|
47 |
+
to aid or provide an second viewpoint of a public facing statement to help determine if something is compliant per the SEC's guidelines. The dataset was crafted by
|
48 |
+
reviewing the SEC Marketing rule, other scenarios, and providing reasoning within the ###n\ Response n\### to help guide the model in reasoning tasks.
|
49 |
+
Further versions will be reviewed more for accuracy, bias, and more data.
|
50 |
+
|
51 |
+
<!-- -->
|
52 |
|
53 |
### Direct Use
|
54 |
|
|
|
58 |
|
59 |
### Downstream Use [optional]
|
60 |
|
61 |
+
For use by marketing and compliance finance teams to assist in determination and interpretation of SEC Marketing rule and other SEC interpretations. No outputs should be guaranteed as fact,
|
62 |
+
and review of data is encouraged. This is to simply assist, and aid those in remembering certain aspects and interpretation of aspects of the long SEC Marketing guidelines
|
63 |
+
amongst other SEC rulings.
|
64 |
+
|
65 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
66 |
|
67 |
[More Information Needed]
|
68 |
|
69 |
### Out-of-Scope Use
|
70 |
|
71 |
+
This model should not be intended to be used as fact, as evidence/proof in a trial hearing, or be used as indication of innocence in an SEC audit/investigation.
|
72 |
+
This model should be used by professionals deeply familiar with the SEC's guidelines and compliance procedures.
|
73 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
74 |
|
75 |
[More Information Needed]
|
76 |
|
77 |
## Bias, Risks, and Limitations
|
78 |
|
79 |
+
This is the first model iteration, and has not be fully reviewed by multiple professional peers for its accuracy, bias, and output variations.
|
80 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
|
81 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
82 |
|
83 |
[More Information Needed]
|
84 |
|
85 |
### Recommendations
|
86 |
|
87 |
+
<!-- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. -->
|
|
|
88 |
|
89 |
## How to Get Started with the Model
|
90 |
|