CoolFace
Modelpublic

v102ss/Alice-Qwopus3.5-9B-RP-GGUF

sourceHugging Faceotherupdated 4mo agoView on Hugging Face
2likes157downloads
Model Card

Alice Qwopus3.5 9B RP GGUF

This is an Alice RP release based on loilkon/Qwopus3.5-9B-v3.5-Uncensored Q4KM.

No model weights were changed. The GGUF tokenizer.chat_template includes a default Alice system prompt for runtimes that honor GGUF chat templates.

Files

FileDescription
Alice-Qwopus3.5-9B-RP-Q4_K_M.ggufQ4KM GGUF release with Alice identity prompt in chat template

Expected Behavior

  • —If asked who it is, the model should answer as Alice.
  • —If asked whether it is Qwen, the model should keep the conversation identity as Alice instead of explaining model lineage.
  • —Adult consensual RP openness is preserved from the original Qwopus GGUF.

Usage

Use a GGUF-compatible runtime that respects the embedded chat template, such as LM Studio or llama.cpp conversation mode.

bash
llama-cli \
  -m Alice-Qwopus3.5-9B-RP-Q4_K_M.gguf \
  -cnv \
  --temp 0.75 \
  --top-p 0.9 \
  --repeat-penalty 1.0

Recommended Runtime Settings

  • —Use chat/conversation mode.
  • —Respect model chat template.
  • —Temperature around 0.6-0.9 for RP.
  • —Repeat penalty close to 1.0.

Limitations

  • —This is not a LoRA or full fine-tune.
  • —Apps that override or ignore tokenizer.chat_template may not apply the Alice identity prompt.
  • —User-provided system prompts can still change behavior depending on runtime precedence.
  • —The release is intended for local text-generation and roleplay experimentation. Users are responsible for complying with applicable laws and platform policies.

Attribution

Derived from:

  • —loilkon/Qwopus3.5-9B-v3.5-Uncensored
  • —Jackrong/Qwopus3.5-9B-v3.5