Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,49 @@
|
|
1 |
---
|
2 |
license: other
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: other
|
3 |
---
|
4 |
+
|
5 |
+
Alpac(ino) stands for Alpaca Integrated Narrative Optimization.
|
6 |
+
|
7 |
+
This model is a triple model merge of (Alpaca+(CoT+Storytelling)), resulting in a comprehensive boost in Alpaca's reasoning and story writing capabilities.
|
8 |
+
Alpaca was chosen as the backbone of this merge to ensure Alpaca's instruct format remains dominant.
|
9 |
+
|
10 |
+
Below is one use case example of what is possible when using Alpac(ino) in a convenient language model interface such as Text-Generation-WebUI or KoboldAI:
|
11 |
+
An infinite text-based adventure game can be setup by switching to chat mode (in this case username is Player and AI is Narrator) and tailoring the following
|
12 |
+
template in the context/memory section of the interface:
|
13 |
+
|
14 |
+
Make Narrator function as a text based adventure game that responds with verbose, detailed, and creative descriptions of what happens next after Player's response.
|
15 |
+
Make Player function as the player input for Narrator's text based adventure game, controlling a character named (insert character name here, their short bio, and
|
16 |
+
whatever quest or other information to keep consistent in the interaction).
|
17 |
+
|
18 |
+
If using either KAI or TGUI for model inference, testing subjectively suggests ideal presets are "Storywriter" (temp raised to 1.1) or "Godlike" with context tokens
|
19 |
+
maxed at 2048 and max generation tokens ~680 or greater. This model is intelligent enough to determine when to stop writing, and will rarely use half those tokens;
|
20 |
+
however verbosity will vary depending on provided instructions.
|
21 |
+
|
22 |
+
Legalese:
|
23 |
+
This release contains modified weights from the LLaMA-13b model. This model is under a non-commercial
|
24 |
+
license. You should only use this repository if you have been granted access to the model by filling
|
25 |
+
out the form below-
|
26 |
+
https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform
|
27 |
+
Llama models (7b, 13b, 33b, 65b) are all property of Meta AI and are intended for research purposes.
|
28 |
+
This release is commensurate with good faith that those who download and/or utilize this model have
|
29 |
+
been granted research access through the provided form.
|
30 |
+
|
31 |
+
Obligatory:
|
32 |
+
This model may output offensive text and/or infactual statements; do not use this model for advice
|
33 |
+
in any domain, especially medical or mental health advice. Meta AI and I are not liable for improper
|
34 |
+
use or any damages, percieved or otherwise.
|
35 |
+
|
36 |
+
Sourced LoRA Credits:
|
37 |
+
|
38 |
+
ChanSung's exellently made Alpaca LoRA
|
39 |
+
https://huggingface.co/chansung/alpaca-lora-13b
|
40 |
+
https://huggingface.co/datasets/yahma/alpaca-cleaned
|
41 |
+
https://github.com/gururise/AlpacaDataCleaned
|
42 |
+
|
43 |
+
magicgh's valuable CoT LoRA
|
44 |
+
https://huggingface.co/magicgh/llama13b-lora-cot
|
45 |
+
https://huggingface.co/datasets/QingyiSi/Alpaca-CoT
|
46 |
+
https://github.com/PhoebusSi/alpaca-CoT
|
47 |
+
|
48 |
+
GamerUntouch's unique Storytelling LoRA
|
49 |
+
https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs
|