Update README.md
Browse files
README.md
CHANGED
@@ -10,9 +10,9 @@ not include a preliminary finetuning pass on several thousands short stories. In
|
|
10 |
generating on its own the kind of stories that were included there; its training data appears to be quite diverse and does not
|
11 |
seem to have been filtered for content type.
|
12 |
|
13 |
-
Due to software limitations, finetuning didn't take advantage yet of the Sliding Window Attention (SWA) which would have allowed
|
14 |
-
to use longer conversations in the training data. Thus, this version of LimaRP should be considered an
|
15 |
-
will be updated in the future
|
16 |
|
17 |
For more details about LimaRP, see the model page for the [previously released v2 version for Llama-2](https://huggingface.co/lemonilia/limarp-llama2-v2).
|
18 |
Most details written there apply for this version as well. Generally speaking, LimaRP is a longform-oriented, novel-style
|
|
|
10 |
generating on its own the kind of stories that were included there; its training data appears to be quite diverse and does not
|
11 |
seem to have been filtered for content type.
|
12 |
|
13 |
+
**Due to software limitations, finetuning didn't take advantage yet of the Sliding Window Attention (SWA) which would have allowed
|
14 |
+
to use longer conversations in the training data. Thus, this version of LimaRP should be considered an _initial finetuning attempt_ and
|
15 |
+
will be updated in the future.**
|
16 |
|
17 |
For more details about LimaRP, see the model page for the [previously released v2 version for Llama-2](https://huggingface.co/lemonilia/limarp-llama2-v2).
|
18 |
Most details written there apply for this version as well. Generally speaking, LimaRP is a longform-oriented, novel-style
|