Update README.md
Browse files
README.md
CHANGED
|
@@ -6,14 +6,20 @@ tags: []
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
-
|
| 10 |
|
| 11 |
|
| 12 |
## Model Details
|
| 13 |
|
| 14 |
### Model Description
|
| 15 |
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 19 |
|
|
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
This model aims to optimize QA & summerization tasks for the capstone project "Edge LLM - Reducing LLM Memory Footprint to < 2GB" in UW, sponsered by Amazon.
|
| 10 |
|
| 11 |
|
| 12 |
## Model Details
|
| 13 |
|
| 14 |
### Model Description
|
| 15 |
|
| 16 |
+
Base model is Fighoture/Llama-2-7b-chat-shortgpt-with-angular-25-percent, which has been pruned with shortgpt by 25%(8) layers according to angular distance.
|
| 17 |
+
|
| 18 |
+
This model is fine-tuned by a combination of dataset including:
|
| 19 |
+
|
| 20 |
+
1. Randomly-selected 2.5k sample of sharegpt dataset.
|
| 21 |
+
2. Randomly-selected 1.25k sample of stanford gpt4 alpaca dataset, whcih is one part from tuluv2.
|
| 22 |
+
3. Randomly-selected 1.25k sample of openassistant English dataset.
|
| 23 |
|
| 24 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 25 |
|