Update README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,11 @@ This model can be used for entertainment purposes and as a creative writing assi
|
|
20 |
|
21 |
## Usage with Kobold AI Colab
|
22 |
|
23 |
-
Open the code that loads the models and replace a path with "rexwang8/qilin-lit-6b" and select that model.
|
|
|
|
|
|
|
|
|
24 |
|
25 |
## Example Code
|
26 |
|
@@ -46,6 +50,8 @@ Fine-tuned version of EleutherAI/gpt-j-6B (https://huggingface.co/EleutherAI/gpt
|
|
46 |
|
47 |
3150 steps, 1 epoch trained on 550 MB of primarily Xianxia genre Webnovels. (Translated to English)
|
48 |
|
|
|
|
|
49 |
---
|
50 |
|
51 |
## Team members and Acknowledgements
|
|
|
20 |
|
21 |
## Usage with Kobold AI Colab
|
22 |
|
23 |
+
Open the code that loads the models and replace a path with "rexwang8/qilin-lit-6b" and select that model. If you get a large malloc error during the tensor loading step, this will be resolved in the next major version.
|
24 |
+
|
25 |
+
## Usage with Kobold AI Local
|
26 |
+
|
27 |
+
Load at AI/load a model from it's directory. Model name is "rexwang8/qilin-lit-6b". If you get a config.json not found error, reload the program and give it some time to find your gpus.
|
28 |
|
29 |
## Example Code
|
30 |
|
|
|
50 |
|
51 |
3150 steps, 1 epoch trained on 550 MB of primarily Xianxia genre Webnovels. (Translated to English)
|
52 |
|
53 |
+
ps. lit stands for literature, not related to Anthony's Lit model
|
54 |
+
|
55 |
---
|
56 |
|
57 |
## Team members and Acknowledgements
|