Update README.md
Browse files
README.md
CHANGED
@@ -131,19 +131,17 @@ Quantitative easing is a monetary policy tool used by central banks to stimulate
|
|
131 |
- max_grad_norm = 0.3
|
132 |
- warmup_ratio = 0.03
|
133 |
|
134 |
-
## Model Limitations
|
135 |
-
Potential Biases: With its fine-tuning centered on financial conversations sources, inherent biases from these sources may reflect in the model's outputs.
|
136 |
-
|
137 |
## Licensing
|
138 |
The FinanceConnect model, developed by CeADAR Connect Group, combines the licensing frameworks of Llama2, FinTalk-8k and Alpaca. Under Meta's terms, users are granted a non-exclusive, worldwide, non-transferable, royalty-free limited license for the use and modification of Llama Materials, inclusive of the Llama2 model and its associated documentation. When redistributing, the provided Agreement and a specific attribution notice must be included. In alignment with the FinTalk dataset's licensing and Alpaca dataset's licensing, the model is also distributed under the "cc-by-nc-4.0" license.
|
139 |
|
140 |
-
##
|
|
|
141 |
FinanceConnect is specifically tailored for finanical discussions and knowledge. It is not optimized for:
|
142 |
- General, non-AI-related conversations.
|
143 |
- Domain-specific tasks outside financial tasks.
|
144 |
- Direct interfacing with physical devices or applications.
|
145 |
|
146 |
-
|
147 |
- Dataset Biases: The FinTalk-19k and Alpaca dataset may contain inherent biases that influence the model's outputs.
|
148 |
- Over-reliance: The model is an aid, not a replacement for human expertise. Decisions should be made with careful consideration.
|
149 |
- Content Understanding: The model lacks human-like understanding and cannot judge the veracity of knowledge.
|
|
|
131 |
- max_grad_norm = 0.3
|
132 |
- warmup_ratio = 0.03
|
133 |
|
|
|
|
|
|
|
134 |
## Licensing
|
135 |
The FinanceConnect model, developed by CeADAR Connect Group, combines the licensing frameworks of Llama2, FinTalk-8k and Alpaca. Under Meta's terms, users are granted a non-exclusive, worldwide, non-transferable, royalty-free limited license for the use and modification of Llama Materials, inclusive of the Llama2 model and its associated documentation. When redistributing, the provided Agreement and a specific attribution notice must be included. In alignment with the FinTalk dataset's licensing and Alpaca dataset's licensing, the model is also distributed under the "cc-by-nc-4.0" license.
|
136 |
|
137 |
+
## Model Limitations
|
138 |
+
### Out-of-Scope Use
|
139 |
FinanceConnect is specifically tailored for finanical discussions and knowledge. It is not optimized for:
|
140 |
- General, non-AI-related conversations.
|
141 |
- Domain-specific tasks outside financial tasks.
|
142 |
- Direct interfacing with physical devices or applications.
|
143 |
|
144 |
+
### Bias, Risks, and Limitations
|
145 |
- Dataset Biases: The FinTalk-19k and Alpaca dataset may contain inherent biases that influence the model's outputs.
|
146 |
- Over-reliance: The model is an aid, not a replacement for human expertise. Decisions should be made with careful consideration.
|
147 |
- Content Understanding: The model lacks human-like understanding and cannot judge the veracity of knowledge.
|