sohi-g commited on
Commit
a9c47cd
1 Parent(s): c8fe58f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -0
README.md CHANGED
@@ -1,3 +1,50 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - briefai/LongShort-Dataset
5
+ language:
6
+ - en
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - pytorch
10
+ - mistral
11
+ - Gen-AI
12
+ - Finance
13
+ - KPI Extraction
14
  ---
15
+ # LongShort-Mistral-7B
16
+ - Model creator: [Brief AI](https://huggingface.co/briefai)
17
+ - Original model: [Mistral 7B Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
18
+
19
+ ### Model Description
20
+
21
+ This model leverages Mistral-7B architecture to extract financial KPIs from the earnings call documents.
22
+
23
+ ## Prompt template: LongShort-Mistral-7B
24
+
25
+ ```
26
+ [INST]Given the context, answer the question.
27
+
28
+ ### Question:
29
+ Extract all the finance-based performance indicators and evaluation metrics.
30
+
31
+ ### Context:
32
+ {context}
33
+
34
+ ### Answer:
35
+ [/INST]
36
+
37
+ ```
38
+
39
+ ## Uses
40
+
41
+ Financial KPI Extraction
42
+
43
+
44
+ ## Evaluation Results
45
+
46
+ Accuracy of the model = KPIs Found / ((KPIs Found) + (KPIs Not Found))
47
+
48
+ LongShort-Mistral-7B is giving 48% accuracy on a validation set of 10% of the original training dataset.
49
+
50
+ ## Thanks