Update README.md
Browse files
README.md
CHANGED
@@ -41,7 +41,7 @@ inference:
|
|
41 |
do_sample: True
|
42 |
top_p: 0.95
|
43 |
top_k: 20
|
44 |
-
temperature: 0.
|
45 |
repetition_penalty: 3.5
|
46 |
|
47 |
---
|
@@ -55,11 +55,14 @@ It achieves the following results on the evaluation set:
|
|
55 |
|
56 |
## Model description
|
57 |
|
58 |
-
-
|
|
|
|
|
59 |
|
60 |
## Intended uses & limitations
|
61 |
|
62 |
-
- [ai-msgbot](https://github.com/pszemraj/ai-msgbot)
|
|
|
63 |
|
64 |
## Training and evaluation data
|
65 |
|
|
|
41 |
do_sample: True
|
42 |
top_p: 0.95
|
43 |
top_k: 20
|
44 |
+
temperature: 0.3
|
45 |
repetition_penalty: 3.5
|
46 |
|
47 |
---
|
|
|
55 |
|
56 |
## Model description
|
57 |
|
58 |
+
- a basic dialogue model for conversation. It can be used as a chatbot.
|
59 |
+
- check out a [simple demo here](https://huggingface.co/spaces/ethzanalytics/dialogue-demo)
|
60 |
+
|
61 |
|
62 |
## Intended uses & limitations
|
63 |
|
64 |
+
- usage is designed for integrating with this repo: [ai-msgbot](https://github.com/pszemraj/ai-msgbot)
|
65 |
+
- the main specific information to know is that the model generates whole conversations between two entities, `person alpha` and `person beta`. These entity names are used functionally as custom `<bos>` tokens to extract when one response ends and another begins.
|
66 |
|
67 |
## Training and evaluation data
|
68 |
|