Update README.md
Browse files
README.md
CHANGED
@@ -75,6 +75,10 @@ ASSISTANT:
|
|
75 |
- Capybara is trained mostly on multi-turn, long context, highly curated and cleaned GPT-4 conversations with real humans.
|
76 |
|
77 |
For these reasons, it's reccomended to give Capybara a try if you want to have multi-turn conversations and/or long context communication.
|
|
|
|
|
|
|
|
|
78 |
|
79 |
## Limitations
|
80 |
|
@@ -112,6 +116,3 @@ The following are benchmarks we checked for contamination for:
|
|
112 |
|
113 |
- GPT4All
|
114 |
|
115 |
-
## Benchmarks! (Important to note that all the mentioned benchmarks are in a single-turn dataset setting, Capybara should excel even further at multi-turn conversational tasks.)
|
116 |
-
|
117 |
-
![Capybara](https://i.imgur.com/n8lkmyK.png)
|
|
|
75 |
- Capybara is trained mostly on multi-turn, long context, highly curated and cleaned GPT-4 conversations with real humans.
|
76 |
|
77 |
For these reasons, it's reccomended to give Capybara a try if you want to have multi-turn conversations and/or long context communication.
|
78 |
+
|
79 |
+
## Benchmarks! (Important to note that all the mentioned benchmarks are in a single-turn dataset setting, Capybara should excel even further at multi-turn conversational tasks.)
|
80 |
+
|
81 |
+
![Capybara](https://i.imgur.com/n8lkmyK.png)
|
82 |
|
83 |
## Limitations
|
84 |
|
|
|
116 |
|
117 |
- GPT4All
|
118 |
|
|
|
|
|
|