IkariDev commited on
Commit
6cc39d5
1 Parent(s): 6a3baf9

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ ---
4
+
5
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/VKX2Z2yjZX5J8kXzgeCYO.png)
6
+
7
+
8
+ ---
9
+
10
+ # Disclaimer:
11
+ ## This is a ***TEST*** version, don't expect everything to work!!!
12
+
13
+ You may use our custom prompting format, or simple alpaca. **(Choose which fits best for you!)**
14
+
15
+ ---
16
+
17
+
18
+ # This model is a collab between [IkariDev](https://huggingface.co/IkariDev) and [Undi](https://huggingface.co/Undi95)!
19
+
20
+ Tired of the same merges everytime? Here it is, the Noromaid-13b-v0.1.1 model. Suitable for RP, ERP and general stuff.
21
+
22
+ [Recommended settings - No settings yet(Please suggest some over in the Community tab!)]
23
+
24
+ <!-- description start -->
25
+ ## Description
26
+
27
+ <!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
28
+
29
+ This repo contains GGUF files of Noromaid-13b-v0.1.1.
30
+
31
+ ## Changelog what should be fixed from the last version (0.1):
32
+ -Fixed somes issues where the model had a hard time grasping at the character card/persona, logical error and the following of the story/chat.
33
+ -Fixed some logical issue.
34
+ -Fixed some OOC leaking at the end of some reply (tested without stopping string).
35
+ -Fixed an obscure crash in Koboldcpp where the model refused to output anymore when context was full in some case.
36
+
37
+ [FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-13b-v0.1.1)
38
+
39
+ <!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->
40
+
41
+ <!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->
42
+
43
+ <!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->
44
+
45
+ <!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->
46
+
47
+ <!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->
48
+
49
+ [GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-13b-v0.1.1-GGUF)
50
+ <!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
51
+
52
+ ## Ratings:
53
+
54
+ Note: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!
55
+
56
+ No ratings yet!
57
+
58
+ If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
59
+
60
+ <!-- description end -->
61
+ <!-- prompt-template start -->
62
+ ## Prompt template: Custom format, or Alpaca
63
+
64
+ ### Custom format:
65
+ SillyTavern config files: [Context](https://files.catbox.moe/x85uy1.json), [Instruct](https://files.catbox.moe/ttw1l9.json).
66
+
67
+ ### Alpaca:
68
+ ```
69
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
70
+
71
+ ### Instruction:
72
+ {prompt}
73
+
74
+ ### Response:
75
+
76
+ ```
77
+
78
+ ## Training data used:
79
+ - [no_robots dataset](https://huggingface.co/Undi95/Llama2-13B-no_robots-alpaca-lora) let the model have more human behavior, enhances the output.
80
+ - [Private RP dataset] New data from a new and never used before dataset, add fresh data, no LimaRP spam, this is 100% new.
81
+
82
+ ## Others
83
+
84
+ Undi: If you want to support me, you can [here](https://ko-fi.com/undiai).
85
+
86
+ IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek