Commit
•
645cba0
1
Parent(s):
dd47c17
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,9 @@ tags:
|
|
| 32 |
# Model Overview
|
| 33 |
This is a fine-tune of the FLAN-T5-Base model from Google. This was trained for 3 epochs on the "samsum" dataset in order to summarise chat logs.
|
| 34 |
|
| 35 |
-
There
|
|
|
|
|
|
|
| 36 |
|
| 37 |
## Intended Use
|
| 38 |
|
|
@@ -45,7 +47,7 @@ The model has been fine-tuned on the samsum dataset, which contains conversation
|
|
| 45 |
|
| 46 |
## Limitations and Ethical Considerations
|
| 47 |
|
| 48 |
-
As with any language model, the FLAN-T5-
|
| 49 |
|
| 50 |
1. **Limited Context Understanding**: The model's performance heavily relies on the context provided in the chat logs. It may not fully understand the nuances of the conversation, leading to occasional inaccuracies in the generated summaries.
|
| 51 |
|
|
|
|
| 32 |
# Model Overview
|
| 33 |
This is a fine-tune of the FLAN-T5-Base model from Google. This was trained for 3 epochs on the "samsum" dataset in order to summarise chat logs.
|
| 34 |
|
| 35 |
+
There are other models sizes available in this same series:
|
| 36 |
+
* [ChatSum-Large (783M)](https://huggingface.co/KoalaAI/ChatSum-Large)
|
| 37 |
+
* [ChatSum-Small (77M)](https://huggingface.co/KoalaAI/ChatSum-Small)
|
| 38 |
|
| 39 |
## Intended Use
|
| 40 |
|
|
|
|
| 47 |
|
| 48 |
## Limitations and Ethical Considerations
|
| 49 |
|
| 50 |
+
As with any language model, the FLAN-T5-Base model has certain limitations and potential ethical considerations:
|
| 51 |
|
| 52 |
1. **Limited Context Understanding**: The model's performance heavily relies on the context provided in the chat logs. It may not fully understand the nuances of the conversation, leading to occasional inaccuracies in the generated summaries.
|
| 53 |
|