Update README.md
Browse files
README.md
CHANGED
|
@@ -27,8 +27,7 @@ finished!
|
|
| 27 |
|
| 28 |
```
|
| 29 |
|
| 30 |
-
###
|
| 31 |
-
|
| 32 |
The model training (and the ai-msgbot scripts) "force" GPT-2 to generate text in a chat-like structure. If you want non-garbage outputs, these need to be specified manually:
|
| 33 |
|
| 34 |
```
|
|
@@ -40,4 +39,8 @@ then model will respond, ideally with person beta: "response text"
|
|
| 40 |
|
| 41 |
---
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
|
|
|
| 27 |
|
| 28 |
```
|
| 29 |
|
| 30 |
+
### examples with Inference API
|
|
|
|
| 31 |
The model training (and the ai-msgbot scripts) "force" GPT-2 to generate text in a chat-like structure. If you want non-garbage outputs, these need to be specified manually:
|
| 32 |
|
| 33 |
```
|
|
|
|
| 39 |
|
| 40 |
---
|
| 41 |
|
| 42 |
+
- the default inference API examples should work _okay_
|
| 43 |
+
- an ideal test would be explicitly adding `person beta` to the **end** of the prompt text. The model is forced to respond to the entered chat prompt instead of adding to the entered prompt and then responding to that (which may cut off the response text due to the Inference API limits).
|
| 44 |
+
|
| 45 |
+
|
| 46 |
|