Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-3B-Instruct
|
| 3 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
|
|
@@ -33,7 +38,7 @@ Financial question answering
|
|
| 33 |
Analyzing financial reports
|
| 34 |
Conversational AI for finance-related customer support
|
| 35 |
|
| 36 |
-
|
| 37 |
|
| 38 |
### Downstream Use [optional]
|
| 39 |
|
|
@@ -42,7 +47,7 @@ Can be integrated into other systems for:
|
|
| 42 |
Financial sentiment analysis
|
| 43 |
Advanced financial data retrieval pipelines
|
| 44 |
|
| 45 |
-
|
| 46 |
|
| 47 |
### Out-of-Scope Use
|
| 48 |
|
|
@@ -64,7 +69,6 @@ Limitations: Focused on English financial data and may not generalize to other l
|
|
| 64 |
|
| 65 |
### Recommendations
|
| 66 |
|
| 67 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 68 |
|
| 69 |
Use the model with a RAG for best results
|
| 70 |
|
|
@@ -101,9 +105,7 @@ Dropout: 0.1
|
|
| 101 |
Optimizer: AdamW with learning rate 2e-5.
|
| 102 |
Hardware: Trained on consumer-grade GPUs (NVIDIA L4).
|
| 103 |
|
| 104 |
-
#### Preprocessing [optional]
|
| 105 |
|
| 106 |
-
[More Information Needed]
|
| 107 |
|
| 108 |
|
| 109 |
#### Training Hyperparameters
|
|
@@ -118,7 +120,6 @@ Batch Size: 32
|
|
| 118 |
Training Time: Approximately 24 hours
|
| 119 |
|
| 120 |
|
| 121 |
-
|
| 122 |
-
### Framework versions
|
| 123 |
|
| 124 |
- PEFT 0.13.2
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-3B-Instruct
|
| 3 |
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
datasets:
|
| 6 |
+
- gbharti/wealth-alpaca_lora
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
---
|
| 10 |
|
| 11 |
|
|
|
|
| 38 |
Analyzing financial reports
|
| 39 |
Conversational AI for finance-related customer support
|
| 40 |
|
| 41 |
+
|
| 42 |
|
| 43 |
### Downstream Use [optional]
|
| 44 |
|
|
|
|
| 47 |
Financial sentiment analysis
|
| 48 |
Advanced financial data retrieval pipelines
|
| 49 |
|
| 50 |
+
|
| 51 |
|
| 52 |
### Out-of-Scope Use
|
| 53 |
|
|
|
|
| 69 |
|
| 70 |
### Recommendations
|
| 71 |
|
|
|
|
| 72 |
|
| 73 |
Use the model with a RAG for best results
|
| 74 |
|
|
|
|
| 105 |
Optimizer: AdamW with learning rate 2e-5.
|
| 106 |
Hardware: Trained on consumer-grade GPUs (NVIDIA L4).
|
| 107 |
|
|
|
|
| 108 |
|
|
|
|
| 109 |
|
| 110 |
|
| 111 |
#### Training Hyperparameters
|
|
|
|
| 120 |
Training Time: Approximately 24 hours
|
| 121 |
|
| 122 |
|
| 123 |
+
|
|
|
|
| 124 |
|
| 125 |
- PEFT 0.13.2
|