IHaveNoClueAndIMustPost
commited on
Commit
•
05c490f
1
Parent(s):
caea664
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- not-for-all-audiences
|
7 |
+
- llama
|
8 |
+
- llama-2
|
9 |
+
- meta
|
10 |
+
- pytorch
|
11 |
+
- transformers
|
12 |
+
- text-generation
|
13 |
+
- storytelling
|
14 |
+
- storywriting
|
15 |
+
- stories
|
16 |
+
- writing
|
17 |
+
---
|
18 |
+
A couple/multi of GGML conversions of the FrankesteinsMonster-13B merge by [Blackroot](https://huggingface.co/Blackroot). Please see the original [repo](https://huggingface.co/Blackroot/FrankensteinsMonster-13B) for full description and full credits, short summary follows below:<br><br>
|
19 |
+
This is a frankenstein model merge of [Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) + [Llama-2-13B-Storywriter-LORA](https://huggingface.co/Blackroot/Llama-2-13B-Storywriter-LORA) + [limarp-llama2](https://huggingface.co/lemonilia/limarp-llama2)
|
20 |
+
. Both lora merges were done at full weight (1:1:1 ratio)
|
21 |
+
|
22 |
+
Prompt Format
|
23 |
+
|
24 |
+
The model follows the Alpaca prompt format:
|
25 |
+
|
26 |
+
### Instruction:
|
27 |
+
\<prompt\>
|
28 |
+
|
29 |
+
### Response:
|
30 |
+
\<leave a newline blank for model to respond\>
|