license: apache-2.0
base_model:
- Qwen/QwQ-32B
tags:
- axolotl
- reasoning
- qwen2
pipeline_tag: text-generation
language:
- en
🌙 CardThinker-v3
WoonaAi presents...
🚀 Overview
CardThinker is an offshoot of the CardProjector series, but with the possibility of reasoning. CardProjector and CardThinker is a specialized series of language models, fine-tuned to generate character cards for SillyTavern and for creating characters in general. These models are designed to assist creators and roleplayers by automating the process of crafting detailed and well-structured character cards, ensuring compatibility with SillyTavern's format.
✨ What's new in v3?
- Colossal improvement in the model's ability to develop characters using ordinary natural language (bypassing strictly structured formats).
- Colossal improvement in the model's ability to edit characters.
- The ability to create a character in the Silly Tavern json format, which is ready for import, has been restored and improved.
- Added the ability to convert any character into the Silly Tavern json format (absolutely any character description, regardless of how well it is written or in what format. Whether it’s just chaotic text or another structured format.)
- Added the ability to generate, edit, and convert characters in YAML format (highly recommended; based on my tests, the quality of characters in YAML format significantly surpasses all other character representation formats).
- Significant improvement in creative writing.
- Significantly enhanced logical depth in character development.
- Significantly improved overall stability of all models (models are no longer tied to a single format; they are capable of working in all human-readable formats, and infinite generation loops in certain scenarios have been completely fixed).
💡 Usage Recommendations
Reasoning mode:
This model can be used in two modes: reasoning and standard. The standard mode is enabled by default. However, if you need the advanced reasoning mode with its chain-of-thought capability (I strongly recommend using it, as it significantly improves the quality of the generated cards), you must initiate the model's response starting with the following line:<think>
Okay, user is asking me to
In SillyTavern, you can find this setting under "AI Response Formatting - Start Reply With" and simply paste the line above.
In other GUIs that lack a similar feature, you can try this workaround:
- Send your request.
- Receive the first few tokens from the model.
- Stop the generation.
- Delete what the model has generated.
- Manually edit its response by inserting the line
<think>\nOkay, user is asking me toat the very beginning. - Prompt the model to continue generating its response from there.
This alternative method has also worked for me, although it is more cumbersome.
Chat history: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content! (From official Qwen QwQ usage tips)
Chat Template: ChatML
Balanced output:
Temperature: 0.1-0.2
Top-P: 0.92
Rp.Pen: 1.07
Top-K: 100
Rep Pen Range: 360
Rep Pen Slope: 0.7
Ready-to-use SillyTavern preset: here
The character creation process: Based on my tests, I would recommend the following approach. To create a well-developed and structured character, I suggest first asking the model to generate the character in a standard, natural format (meaning you shouldn't request formats like YAML or JSON right away), allowing it to describe the character in plain, understandable text. Then, if needed, ask for any necessary adjustments. Once you're satisfied with the result, request the final version to be converted into YAML format. Why YAML? It's an ideal format for structuring and summarizing a character from your chat story. This format is human-readable, and its clear structure is very well processed by RP models (from my tests, it’s even better in some ways than XML). You can simply copy the entire YAML output and paste it into the Description field in Silly Tavern. Alternatively, you can ask the model to convert the resulting card into JSON while leaving the YAML description untouched. I have found this method of using CardProjector v3 to be the most effective.
💬 Example Conversation
CardProjector 24B v3 Chat from koboldcpp
⚠️ Safety
This model learned on cards for Silly Tavern. I think comments are unnecessary here...
🔧 Technical Specs
Base Model: Qwen/QwQ-32B License: Apache-2.0 Language: English