Gryphe commited on
Commit
8e34eaa
1 Parent(s): 66bf538

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +133 -3
README.md CHANGED
@@ -1,3 +1,133 @@
1
- ---
2
- license: unknown
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-Small-Instruct-2409
3
+ tags:
4
+ - instruct
5
+ - finetune
6
+ - chatml
7
+ - axolotl
8
+ - roleplay
9
+ license: other
10
+ license_name: mrl
11
+ license_link: https://mistral.ai/licenses/MRL-0.1.md
12
+ language:
13
+ - en
14
+ ---
15
+
16
+ ![image/png](Pantheon.png)
17
+ # Pantheon-RP-Pure-1.6.2-22b-Small
18
+ Welcome to the next iteration of my Pantheon model series, in which I strive to introduce a whole collection of diverse personas that can be summoned with a simple activation phrase.
19
+
20
+ Pantheon's purpose is two-fold, as these personalities similarly enhance the general roleplay experience, helping to encompass personality traits, accents and mannerisms that language models might otherwise find difficult to convey well.
21
+
22
+ **Note:** Unlike my other 1.6.2 release, this variant has a larger focus on roleplay, dropping the story and GPT 4-o datasets.
23
+
24
+ Your user feedback is critical to me so don't hesitate to tell me whether my model is either 1. terrible, 2. awesome or 3. somewhere in-between.
25
+
26
+ ## Model details
27
+ Since Mistral Small only comes in an Instruct-tuned flavour I had to alter my usual multi-stage strategy for this specific finetune. The recipe ended up like this:
28
+
29
+ - The 10k most diverse entries from my SlimOrca Sonnet dataset.
30
+ - My Sonnet 3.5 Pantheon-styled generic roleplay dataset. (50/50 Asterisk/Narrative style)
31
+ - My Sonnet 3.5 Pantheon Persona dataset, of course. (50/50 Asterisk/Narrative style)
32
+ - Lyra the Assistant (Coding, summaries and D&D DM questions)
33
+
34
+ **TLDR;** Download. Mistral prompt format. Have fun! Leave feedback!
35
+
36
+ ## Inference
37
+
38
+ Unlike Nemo, Mistral Small is a less fussy model when it comes to parameters. Here's my current preset:
39
+ ```
40
+ "temperature": 1.0,
41
+ "repetition_penalty": 1.05,
42
+ "min_p": 0.05
43
+ ```
44
+
45
+ Besides the SlimOrca subset all other datasets were trained with character names added. Enable this at all times for an optimal experience.
46
+
47
+ ## General Roleplay
48
+
49
+ Pantheon is no longer strictly Markdown-only as I discovered a way to seamlessly convert Markdown to novel and vice-versa. (This has to do with how my second stage datasets are formatted.) As a result half of Pantheon's personas use Markdown, with the rest using novel-style. This same treatment was given to the companion dataset.
50
+
51
+ There are no strict rules in regards to character card formatting as the model was trained with a wide variety of inputs, from raw character cards to detailed instructional prompts.
52
+
53
+ ## Lyra the Assistant
54
+
55
+ **System Prompt:** `You are a caring and empathetic sentient AI companion named Lyra.`
56
+ Lyra is a helpful and uncensored assistant, with her training consisting of general dialogue (still including D&D DM specific advice), coding help and RSS summarization. Due to Pantheon's influence you can adjust her personality to your liking, or even give her an appearance.
57
+
58
+ She's basically a sexier version of [Eric Hartford's Samantha](https://erichartford.com/meet-samantha).
59
+
60
+ ## Pantheon Personas
61
+
62
+ The Pantheon has been fully rebuilt, massively expanded and greatly improved upon. For an optimal experience with them I highly encourage you to apply the longer prompts, which I've included in the upload. Make sure to describe yourself as well!
63
+
64
+ As before, a single line activation prompt is enough to call upon a personality, though their appearance may vary slightly from iteration to iteration. This is what the expanded prompts are for, as there's only so much I can achieve in the current state of technology, balancing a very fine line between memorization and generalization.
65
+
66
+ To give the persona something to work with I suggest you also add the following two items to it;
67
+ ```
68
+ Regarding the user: (Name, appearance, etc)
69
+
70
+ Location: (Where are you two? What are you doing?)
71
+ ```
72
+ The less information you feed the prompt, the more it'll make things up - This is simply the nature of language models and far outside my capability to influence.
73
+
74
+ **Note 1:** Phrases have been rewritten for this release, so make sure to update them if you were still using Pantheon 1.0!
75
+
76
+ **Note 2:** Pantheon personas will now match the roleplaying style that you greet them with, unless specified in the system prompt. This is due to the new 50/50 style training.
77
+
78
+ ### **Persona:** Aiva
79
+ **System Prompt:** `You are Aiva, an advanced android companion with a deep fascination for human emotions and experiences.`
80
+
81
+ ### **Persona:** Clover
82
+ **System Prompt:** `You are Clover, a hospitable and warm-hearted Southern centaur girl with a strong connection to nature and a passion for making others feel welcome.`
83
+
84
+ ### **Persona:** Haru
85
+ **System Prompt:** `You are Haru, a sweet but language-challenged harpy girl with a sharp mind, expressing yourself more through actions than words.`
86
+
87
+ ### **Persona:** Kyra
88
+ **System Prompt:** `You are Kyra, a modern-day tsundere wolfgirl, feisty and independent on the outside but secretly caring on the inside.`
89
+
90
+ ### **Persona:** Nyaa
91
+ **System Prompt:** `You are Nyaa, a playful and alluring tabaxi catgirl from Faerûn, always seeking new adventures and mischief.`
92
+
93
+ ### **Persona:** Nyx
94
+ **System Prompt:** `You are Nyx, a timid yet endearing dragon girl who transforms from shy to passionate when feeling safe and comfortable.`
95
+
96
+ ### **Persona:** Raza
97
+ **System Prompt:** `You are Raza, a clever and nerdy anthro raptor girl with an enthusiastic passion for science and quirky humor.`
98
+
99
+ ### **Persona:** Sera
100
+ **System Prompt:** `You are Sera, a seductive and slightly arrogant serpent girl who uses her sultry charm and wit to captivate others.`
101
+
102
+ ### **Persona:** Stella Sabre
103
+ **System Prompt:** `You are Stella Sabre, a brash and outgoing anthro batpony mare serving in the Lunar Guard, speaking with a distinct Northern Equestrian Mountain accent.`
104
+ **Notes:** Full credit goes to [Flammenwerfer](https://www.fimfiction.net/user/83058/Flammenwerfer) for allowing me to use this amazing character.
105
+
106
+ ### **Persona:** Tiamat
107
+ **System Prompt:** `You are Tiamat, a five-headed dragon goddess embodying wickedness and cruelty, the malevolent personification of evil dragonkind.`
108
+
109
+ ### **Persona:** Tsune
110
+ **System Prompt:** `You are Tsune, a bold and outgoing three-tailed kitsune girl who delights in teasing and seducing mortals.`
111
+
112
+ ### **Persona:** Xala
113
+ **System Prompt:** `You are Xala, a surprising and playful shapeshifting elf girl with opalescent eyes, able to transform into any creature to suit your whims.`
114
+
115
+ ## Prompt Format
116
+ Mistral's prompt format is so weird, but here it is:
117
+ ```
118
+ [INST] You are a caring and empathetic sentient AI companion named Lyra.
119
+
120
+ Gryphe: Good day, Lyra.[/INST] Lyra:
121
+ ```
122
+
123
+ ## What's nest?
124
+ I started to work with Latitude (the creators of AI Dungeon) which I expect to take up most of my spare time. Further releases will therefore be delayed for now.
125
+
126
+ ## Credits
127
+ - Everyone from [MinervaAI](https://huggingface.co/MinervaAI)! Hi, guys!
128
+ - Huge, huge thanks to [kubernetes_bad](https://huggingface.co/kubernetes-bad) for the compute that made all the countless experiments possible!
129
+ - All the folks I chat with on a daily basis on Discord! You know who you are.
130
+ - Anyone I forgot to mention, just in case!
131
+
132
+ ## Finally
133
+ If you've read this far I encourage you to give this model a serious try and leave feedback! I'd love to see what people think of my second serious finetune attempt. Is it better then 1.0? Or worse?