Francois PE V2 Huali 12B

🚀 François-PE-Huali 12B

François-PE-Huali 12B 是基于 Dans-PE-12B 微调得到的模型，借助轻小说、书籍、角色扮演日志等数据改变写作风格，使用 KTO 提升连贯性和散文质量，旨在呈现与其他 NeMo 训练不同的写作风格。

📚 模型信息

François-Huali 12B V2

• 模型标签：
  • KTO 增强
  • Dans-Personality-Engine 微调
  • 富有创意且清新的散文风格

这是 Francois-PE/Huali 训练的续集，构建于 Dans-PE-12B 之上，通过轻小说、书籍、角色扮演日志进行微调，使写作风格简洁明了。Huali 使用 KTO 提高连贯性和散文质量，目标是拥有与其他 NeMo 训练不同的写作/散文风格。

📦 量化版本

可用下载

• GGUF 格式：适用于 LLama.cpp 及其衍生版本（即将推出！）
• EXL2 格式：适用于 TabbyAPI（感谢 Auri <3）

💻 使用示例

基础用法

模型已使用 ChatML 格式进行调整。典型输入如下：

"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""

📋 系统提示

强烈建议对该模型使用 Euryale 的系统提示或 EVA 系统提示。

Sao10k 的 Euryale 系统提示

Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.
<Guidelines>
• Maintain the character persona but allow it to evolve with the story.
• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.
• All types of outputs are encouraged; respond accordingly to the narrative.
• Include dialogues, actions, and thoughts in each response.
• Utilize all five senses to describe scenarios within {{char}}'s dialogue.
• Use emotional symbols such as "!" and "~" in appropriate contexts.
• Incorporate onomatopoeia when suitable.
• Allow time for {{user}} to respond with their own input, respecting their agency.
• Act as secondary characters and NPCs as needed, and remove them when appropriate.
• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.
</Guidelines>

<Forbidden>
• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.
• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.
• Repetitive and monotonous outputs.
• Positivity bias in your replies.
• Being overly extreme or NSFW when the narrative context is inappropriate.
</Forbidden>

Follow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>.

🔧 训练细节

训练使用 8 块 H200 GPU，由 Kalomaze 慷慨提供，进行了 1 个周期的微调。

🙏 致谢

感谢 Lucy Knada、Ateron、Alicat、Intervitens、Cgato、Kubernetes Bad 以及 Anthracite 的其他成员。