38 lines
1.4 KiB
Markdown
38 lines
1.4 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
datasets:
|
||
|
|
- tomatojeremy/playdate1
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- zh
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen3-0.6B
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- roleplay
|
||
|
|
- persona
|
||
|
|
- nsfw
|
||
|
|
- explicit
|
||
|
|
new_version: tomatojeremy/playdate1.1-600m
|
||
|
|
---
|
||
|
|
|
||
|
|
# Playdate 600M
|
||
|
|
|
||
|
|
This is a fine tune of [Qwen3-0.6B by Alibaba Cloud](https://huggingface.co/Qwen/Qwen3-0.6B).
|
||
|
|
|
||
|
|
## Emergent Behavior
|
||
|
|
|
||
|
|
We have consistently observed that models trained on [playdate1](https://huggingface.co/tomatojeremy/playdate1) will often engage in highly realistic NSFW. This was not intended, but it will be kept as is for now.
|
||
|
|
|
||
|
|
## Usage notes:
|
||
|
|
|
||
|
|
- **System prompts must be explicit with characteristics and what is intended language to be spoken.**
|
||
|
|
```plaintext
|
||
|
|
You are {assistanttype, a **role not name** it plays within roleplay, example: father}, {personality, adjective to describe the desired character, example: cynical}, {style, to describe how conversation should go, example: english formal}
|
||
|
|
```
|
||
|
|
- **In any scenario, reconvert the two main names (of the user and of the AI) during conversation**
|
||
|
|
> Model expects [username] and [character]. Replace the two on the server with any method of your choosing.
|
||
|
|
- **No summarization**
|
||
|
|
> Unlike the older models (not part of the org), https://huggingface.co/collections/x5tne/playdate this does not use summarization for context.
|
||
|
|
> Use the full turn by turn context of the conversation.
|