maywell commited on
Commit
8ea00e8
1 Parent(s): 6af9641

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +56 -0
README.md CHANGED
@@ -1,3 +1,59 @@
1
  ---
2
  license: cc-by-nc-sa-4.0
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-nc-sa-4.0
3
+ language:
4
+ - en
5
  ---
6
+
7
+ > [!TIP]
8
+ > This is official GPTQ. Quantized using train data.
9
+
10
+ # LYNN - AI for Roleplay
11
+
12
+ <img src="./reallynn.png" alt="it's lynn!" width="340"/>
13
+
14
+ > [!TIP]
15
+ > This model is overfitted to the role-playing dataset; normal conversations may not work well.
16
+
17
+ # Soliloquy-L3
18
+
19
+ Soliloquy-L3 is a fast, highly capable roleplaying model designed for immersive, dynamic experiences. Trained on over 250 million tokens of roleplaying data, Soliloquy-L3 has a vast knowledge base, rich literary expression, and support for up to 24k context length. It outperforms existing ~13B models, delivering enhanced roleplaying capabilities.
20
+
21
+ ## Model Info
22
+
23
+ | Context Length | Parameter | Prompt Template | isErp |
24
+ | --- | --- | --- | --- |
25
+ | 24k(24576) | 8B | Llama 3 Chat | Partly |
26
+
27
+ ## Prompt Template
28
+
29
+ Use can you following jinja2 template. Which is identical to chat_template in [tokenizer_config](./tokenizer_config.json).
30
+
31
+ ```
32
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}
33
+ ```
34
+
35
+ ## License
36
+
37
+ This model is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License, under [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/)
38
+
39
+ If you would like to use this model for commercial purposes, please use our proprietary API. (Currently avilable at OpenRouter)
40
+
41
+ For non-commercial use, please adhere to the terms of the CC BY-NC-SA 4.0 license. You are free to share and adapt the model for non-commercial purposes, provided you give appropriate credit, indicate if changes were made, and do not imply endorsement by the licensor.
42
+
43
+ For more information about the CC BY-NC 4.0 license, please visit: https://creativecommons.org/licenses/by-nc-sa/4.0/
44
+
45
+ If you have any questions or would like to inquire about licensing, please contact us.
46
+
47
+ ## Llama 3 Intended Use
48
+
49
+ **Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
50
+
51
+ **Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
52
+
53
+ **Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
54
+
55
+ [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
56
+
57
+ ## Join our Discord
58
+
59
+ [**Join LYNN Discord**](https://discord.gg/xuZVqUyG4Y)