Commit
·
bee4a54
1
Parent(s):
df3e5e5
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,8 +81,9 @@ Model | Average | ARC (25-shot) | He
|
|
| 81 |
--- | --- | --- | --- | --- | ---
|
| 82 |
Locutusque/gpt2-conversational-or-qa | 30.9 | 21.3 | 27.6 | 27.5 | 47.3
|
| 83 |
gpt2 | 30.4 | 21.9 | 31.6 | 27.5 | 40.7
|
| 84 |
-
This model performed excellently in TruthfulQA, outperforming gpt2 by nearly 7 points
|
| 85 |
||||||
|
|
|
|
|
|
|
| 86 |
## Limitations and Bias
|
| 87 |
This model is not suitable for all use cases due to its limited training time on a weak computer. As a result, it may produce irrelevant or nonsensical responses. Additionally, it has not been fine-tuned to remember the chat history, is unable to provide follow-up responses, and it does not know the answer to many questions (it was only fine-tuned to respond in a conversational way). For optimal performance, we recommend using a GPU with at least 4GB of VRAM and downloading the model manually instead of using the Transformers library or deploying it on the Interface API. Here's how you should deploy the model:
|
| 88 |
|
|
|
|
| 81 |
--- | --- | --- | --- | --- | ---
|
| 82 |
Locutusque/gpt2-conversational-or-qa | 30.9 | 21.3 | 27.6 | 27.5 | 47.3
|
| 83 |
gpt2 | 30.4 | 21.9 | 31.6 | 27.5 | 40.7
|
|
|
|
| 84 |
||||||
|
| 85 |
+
|
| 86 |
+
### This model performed excellently in TruthfulQA, outperforming gpt2 by nearly 7 points
|
| 87 |
## Limitations and Bias
|
| 88 |
This model is not suitable for all use cases due to its limited training time on a weak computer. As a result, it may produce irrelevant or nonsensical responses. Additionally, it has not been fine-tuned to remember the chat history, is unable to provide follow-up responses, and it does not know the answer to many questions (it was only fine-tuned to respond in a conversational way). For optimal performance, we recommend using a GPU with at least 4GB of VRAM and downloading the model manually instead of using the Transformers library or deploying it on the Interface API. Here's how you should deploy the model:
|
| 89 |
|