Image-Text-to-Text
Transformers
Safetensors
GGUF
Chinese
English
qwen3_5
joyfox
roleplay
conversational
companion
creative-writing
vision
imatrix
Instructions to use joyfox/JoyFox-Reverie-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use joyfox/JoyFox-Reverie-27B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="joyfox/JoyFox-Reverie-27B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("joyfox/JoyFox-Reverie-27B") model = AutoModelForMultimodalLM.from_pretrained("joyfox/JoyFox-Reverie-27B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use joyfox/JoyFox-Reverie-27B with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M # Run inference directly in the terminal: llama cli -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M # Run inference directly in the terminal: llama cli -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Use Docker
docker model run hf.co/joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
- LM Studio
- Jan
- vLLM
How to use joyfox/JoyFox-Reverie-27B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "joyfox/JoyFox-Reverie-27B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "joyfox/JoyFox-Reverie-27B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
- SGLang
How to use joyfox/JoyFox-Reverie-27B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "joyfox/JoyFox-Reverie-27B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "joyfox/JoyFox-Reverie-27B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "joyfox/JoyFox-Reverie-27B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "joyfox/JoyFox-Reverie-27B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Ollama
How to use joyfox/JoyFox-Reverie-27B with Ollama:
ollama run hf.co/joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
- Unsloth Desktop
- Pi
How to use joyfox/JoyFox-Reverie-27B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "joyfox/JoyFox-Reverie-27B:UD-Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use joyfox/JoyFox-Reverie-27B with Docker Model Runner:
docker model run hf.co/joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
- Lemonade
How to use joyfox/JoyFox-Reverie-27B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Run and chat with the model
lemonade run user.JoyFox-Reverie-27B-UD-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use joyfox/JoyFox-Reverie-27B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use joyfox/JoyFox-Reverie-27B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf joyfox/JoyFox-Reverie-27B:UD-Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "joyfox/JoyFox-Reverie-27B:UD-Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
|
Download README_ZH.md from joyfox/JoyFox-Reverie-27B: direct link, hf CLI and curl.
- Browser
- Download file 12.2 kB
-
https://huggingface.co/joyfox/JoyFox-Reverie-27B/resolve/main/README_ZH.md
- Command line
-
hf download hf://joyfox/JoyFox-Reverie-27B/README_ZH.md
-
curl -L -o README_ZH.md https://huggingface.co/joyfox/JoyFox-Reverie-27B/resolve/main/README_ZH.md
12.2 kB
| license: apache-2.0 | |
| base_model: Qwen/Qwen3.8-27B | |
| library_name: transformers | |
| pipeline_tag: image-text-to-text | |
| language: | |
| - zh | |
| - en | |
| tags: | |
| - joyfox | |
| - roleplay | |
| - conversational | |
| - companion | |
| - creative-writing | |
| - vision | |
| model_name: JoyFox-Reverie-27B | |
| <p align="center"> | |
| <img src="assets/joyfox-reverie-27b-banner.png" alt="JoyFox-Reverie-27B" width="100%"> | |
| </p> | |
| <p align="center"> | |
| <img src="assets/joyfox-reverie-tagline-zh.png" alt="让想象中的角色,走进每一次对话。" width="760"> | |
| </p> | |
| <p align="center"> | |
| <a href="https://huggingface.co/joyfox/JoyFox-Reverie-27B">模型主页</a> · <a href="https://huggingface.co/joyfox/JoyFox-Reverie-27B/blob/main/README.md">English</a> · <a href="https://huggingface.co/joyfox/JoyFox-Reverie-27B/blob/main/README_ZH.md">简体中文</a> | |
| </p> | |
| > 让故事有回响,让日常有陪伴。 | |
| JoyFox-Reverie-27B 是 JoyFox 基于 [Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) 打造的对话模型,面向角色扮演、共同创作故事与朋友式交流。 | |
| “Reverie”意为遐想:你可以认识一个角色,走进一段故事,也可以在一天结束时,找一个熟悉的声音聊聊天。从细致的虚构场景到轻松的日常交流,对话体验由你的设定展开。 | |
| ## ✨ 模型特点 | |
| - **角色对话:**通过人物背景、说话风格、关系与场景提示塑造角色。 | |
| - **朋友式交流:**设定亲切自然的聊天风格,围绕日常话题与个人想法展开对话。 | |
| - **共同叙事:**一起创作场景与对白,明确双方分别控制的人物。 | |
| - **灵活表达:**指定回复语言、叙述视角、篇幅,以及动作与对白的比例。 | |
| - **思考模式控制:**通过附带聊天模板选择直接回复或启用思考。 | |
| - **视觉上下文:**保留上游视觉组件,可通过兼容的处理器与运行框架接入图片和视频。 | |
| ## 🚀 快速开始 | |
| ### 使用 Transformers | |
| 使用支持 Qwen3.8 检查点及其处理器的当前 Transformers 版本。架构加载方式可参考 [Transformers 文档](https://huggingface.co/docs/transformers/model_doc/qwen3_5)。 | |
| ```bash | |
| pip install -U torch transformers accelerate | |
| ``` | |
| 以下示例关闭思考模式,直接开始角色对话: | |
| ```python | |
| import torch | |
| from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration | |
| model_id = "joyfox/JoyFox-Reverie-27B" | |
| processor = AutoProcessor.from_pretrained(model_id) | |
| model = Qwen3_5ForConditionalGeneration.from_pretrained( | |
| model_id, | |
| dtype=torch.bfloat16, | |
| device_map="auto", | |
| ) | |
| messages = [ | |
| {"role": "system", "content": "你是经营海边书店的旧友米拉。自然交谈,保持角色设定,让我自己决定行动。"}, | |
| {"role": "user", "content": "忙了一整天,我推开书店的门。你现在有空聊聊吗?"}, | |
| ] | |
| inputs = processor.apply_chat_template( | |
| messages, | |
| tokenize=True, | |
| add_generation_prompt=True, | |
| enable_thinking=False, | |
| return_dict=True, | |
| return_tensors="pt", | |
| ).to(model.device) | |
| with torch.inference_mode(): | |
| output = model.generate( | |
| **inputs, | |
| max_new_tokens=512, | |
| do_sample=True, | |
| temperature=0.7, | |
| top_p=0.9, | |
| top_k=20, | |
| ) | |
| reply = output[0, inputs["input_ids"].shape[-1]:] | |
| print(processor.decode(reply, skip_special_tokens=True)) | |
| ``` | |
| ### 使用 vLLM 部署 | |
| 下面的命令启动聊天服务,使用 32K 上下文设置。请为 BF16 权重与运行状态分配足够显存;多 GPU 部署时可增加张量并行度。 | |
| ```bash | |
| pip install -U vllm | |
| vllm serve joyfox/JoyFox-Reverie-27B \ | |
| --served-model-name JoyFox-Reverie-27B \ | |
| --dtype bfloat16 \ | |
| --max-model-len 32768 \ | |
| --reasoning-parser qwen3 | |
| ``` | |
| 使用多 GPU 时,添加 `--tensor-parallel-size` 并设置 GPU 数量。上下文容量与并发数取决于可用显存。框架要求与硬件配置可参考 [vLLM Qwen3.8 部署指南](https://recipes.vllm.ai/Qwen/Qwen3.8-27B)。 | |
| ### 调用聊天 API | |
| 服务启动后,发送对话请求: | |
| ```bash | |
| curl http://localhost:8000/v1/chat/completions \ | |
| -H 'Content-Type: application/json' \ | |
| -d '{ | |
| "model": "JoyFox-Reverie-27B", | |
| "messages": [ | |
| { | |
| "role": "system", | |
| "content": "你是旧友米拉。自然交谈,让我自己决定行动。" | |
| }, | |
| { | |
| "role": "user", | |
| "content": "今天有点累,可以陪我聊会儿吗?" | |
| } | |
| ], | |
| "temperature": 0.7, | |
| "top_p": 0.9, | |
| "max_tokens": 512, | |
| "chat_template_kwargs": { | |
| "enable_thinking": false | |
| } | |
| }' | |
| ``` | |
| 多轮聊天时,将每次模型回复和下一条用户消息追加到 `messages` 后再发送请求。服务使用模型附带的聊天模板。 | |
| ### 图片输入 | |
| 使用 Transformers 示例中的模型与处理器,将 `messages` 替换为下面的内容,再执行相同的模板处理与生成步骤: | |
| ```python | |
| messages = [ | |
| {"role": "system", "content": "你是海边书店的店主米拉。描述画面时,区分实际看到的内容与想象。"}, | |
| { | |
| "role": "user", | |
| "content": [ | |
| {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, | |
| {"type": "text", "text": "这张图片里有什么引起你的注意?"}, | |
| ], | |
| }, | |
| ] | |
| ``` | |
| 图片和视频的处理方式取决于运行框架。视频输入格式与媒体参数可参考[上游使用指南](https://huggingface.co/Qwen/Qwen3.8-27B)。 | |
| ## 💬 对话风格 | |
| ### 角色扮演 | |
| 角色提示词可以围绕人物身份、关系与当前场景展开: | |
| ```text | |
| 你是米拉,一间海边小书店的店主,也是我的旧友。 | |
| 说话风格:温和、细心,偶尔带一点冷幽默。 | |
| 当前场景:下雨的傍晚,书店即将打烊。 | |
| 以对白为主,需要时加入简短动作描写。 | |
| 围绕已经建立的事实推进场景,把我的行动与决定留给我。 | |
| ``` | |
| ### 朋友式聊天 | |
| 希望直接交流、不加入虚构场景时,可以这样设定: | |
| ```text | |
| 像一个愿意倾听的朋友一样和我聊天。语气自然、轻松,顺着我提出的话题交流。在有助于对话时提问,也可以表达你的看法,不必把每次回复都变成建议。除非我要求角色扮演,否则不要加入动作描写或舞台旁白。 | |
| ``` | |
| ### 共同创作故事 | |
| ```text | |
| 我们一起创作一个悬疑故事。你控制配角与环境,我控制主角。沿着已经发生的事件推进,逐步引入线索,并为我的下一步决定留下空间。 | |
| ``` | |
| ## 🧠 思考模式 | |
| 直接进行角色聊天时,向聊天模板传入 `enable_thinking=False`。附带模板默认启用思考。 | |
| 需要思考时,可将以下参数传给 `processor.apply_chat_template`: | |
| ```python | |
| chat_options = { | |
| "enable_thinking": True, | |
| "reasoning_effort": "medium", | |
| "preserve_thinking": True, | |
| } | |
| ``` | |
| `reasoning_effort` 支持 `low`、`medium` 与默认的 `xhigh`。`preserve_thinking` 控制此前助手消息中的思考内容是否保留。调用聊天 API 时,将模板参数放入 `chat_template_kwargs`;服务端的 reasoning parser 会区分思考内容与正式回答。 | |
| ## 🎛️ 生成参数 | |
| 快速开始示例使用 temperature `0.7`、top-p `0.9`、top-k `20` 进行直接对话。附带生成配置的默认值为 temperature `1.0`、top-p `0.95`、top-k `20`。 | |
| 可将这些参数作为起点。需要更克制的表达时降低 temperature,希望探索更多措辞时适当提高。建议一次调整一个参数,并为预期回复长度预留足够的输出 token。不同运行框架支持的采样项可能不同。 | |
| ## 💡 使用建议 | |
| - 角色卡保持简洁、明确,区分长期身份与当前场景。 | |
| - 多轮请求携带此前的消息,让模型能够利用已建立的事件与人物关系。 | |
| - 明确双方控制哪些角色,以及模型是否可以主动引入新事件。 | |
| - 直接指定语言、视角与回复长度,让交流风格更贴合你的设定。 | |
| - 长时间对话可维护简短的事实摘要,并保留最近的对话消息。 | |
| - 将虚构对白作为创作内容;需要准确事实时,对相关陈述进行核实。 | |
| ## 📦 GGUF | |
| Q4–Q6 的 UD 量化文件位于 [GGUF](https://huggingface.co/joyfox/JoyFox-Reverie-27B/tree/main/GGUF)。每个主文件均包含 MTP 张量;图片输入请搭配对应的 F16 `mmproj`。 | |
| | 文件 | 大小(GiB) | | |
| |---|---:| | |
| | [JoyFox-Reverie-27B-UD-Q4_K_M.gguf](GGUF/JoyFox-Reverie-27B-UD-Q4_K_M.gguf) | 15.33 | | |
| | [JoyFox-Reverie-27B-UD-Q4_K_S.gguf](GGUF/JoyFox-Reverie-27B-UD-Q4_K_S.gguf) | 14.30 | | |
| | [JoyFox-Reverie-27B-UD-Q4_K_XL.gguf](GGUF/JoyFox-Reverie-27B-UD-Q4_K_XL.gguf) | 16.35 | | |
| | [JoyFox-Reverie-27B-UD-Q5_K_M.gguf](GGUF/JoyFox-Reverie-27B-UD-Q5_K_M.gguf) | 18.41 | | |
| | [JoyFox-Reverie-27B-UD-Q5_K_S.gguf](GGUF/JoyFox-Reverie-27B-UD-Q5_K_S.gguf) | 17.38 | | |
| | [JoyFox-Reverie-27B-UD-Q5_K_XL.gguf](GGUF/JoyFox-Reverie-27B-UD-Q5_K_XL.gguf) | 19.44 | | |
| | [JoyFox-Reverie-27B-UD-Q6_K.gguf](GGUF/JoyFox-Reverie-27B-UD-Q6_K.gguf) | 20.47 | | |
| | [JoyFox-Reverie-27B-UD-Q6_K_L.gguf](GGUF/JoyFox-Reverie-27B-UD-Q6_K_L.gguf) | 22.53 | | |
| | [JoyFox-Reverie-27B-UD-Q6_K_M.gguf](GGUF/JoyFox-Reverie-27B-UD-Q6_K_M.gguf) | 21.50 | | |
| | [JoyFox-Reverie-27B-UD-Q6_K_XL.gguf](GGUF/JoyFox-Reverie-27B-UD-Q6_K_XL.gguf) | 23.56 | | |
| | [mmproj-JoyFox-Reverie-27B-F16.gguf](GGUF/mmproj-JoyFox-Reverie-27B-F16.gguf) | 0.86 | | |
| ### 下载 GGUF | |
| 使用支持 `qwen35` 的当前 llama.cpp 版本。文本聊天只需下载一个主 GGUF;图片输入还需对应的 `mmproj`。下面以 Q4 XL 为例,使用其他档位时替换主模型文件名即可。 | |
| ```bash | |
| pip install -U huggingface_hub | |
| hf download joyfox/JoyFox-Reverie-27B \ | |
| GGUF/JoyFox-Reverie-27B-UD-Q4_K_XL.gguf \ | |
| GGUF/mmproj-JoyFox-Reverie-27B-F16.gguf \ | |
| --local-dir JoyFox-Reverie-27B | |
| cd JoyFox-Reverie-27B | |
| ``` | |
| ### 文本聊天 | |
| 在下载后的模型目录中运行: | |
| ```bash | |
| llama-cli -m GGUF/JoyFox-Reverie-27B-UD-Q4_K_XL.gguf \ | |
| --jinja --reasoning off -c 32768 -ngl all \ | |
| --temp 0.7 --top-p 0.9 --top-k 20 | |
| ``` | |
| `--jinja` 使用模型内置聊天模板,`--reasoning off` 直接生成回复。`-c` 设置上下文长度,可按显存调整;`-ngl all` 将模型卸载到 GPU,显存不足时可减少 GPU 层数。文件大小不包含运行缓冲区与 KV cache 的占用。 | |
| ### 启动聊天服务 | |
| ```bash | |
| llama-server -m GGUF/JoyFox-Reverie-27B-UD-Q4_K_XL.gguf \ | |
| --jinja --reasoning off -c 32768 -ngl all \ | |
| --host 127.0.0.1 --port 8080 | |
| ``` | |
| 服务提供 `http://127.0.0.1:8080` 网页界面,以及 `/v1/chat/completions` 聊天接口: | |
| ```bash | |
| curl http://127.0.0.1:8080/v1/chat/completions \ | |
| -H 'Content-Type: application/json' \ | |
| -d '{"messages":[{"role":"system","content":"You are Mira, my old friend. Speak naturally."},{"role":"user","content":"How was your day?"}],"temperature":0.7,"top_p":0.9,"max_tokens":256}' | |
| ``` | |
| ### 图片输入 | |
| 图片输入使用所选主 GGUF 与配套的 F16 视觉投影文件: | |
| ```bash | |
| llama-cli -m GGUF/JoyFox-Reverie-27B-UD-Q4_K_XL.gguf \ | |
| --mmproj GGUF/mmproj-JoyFox-Reverie-27B-F16.gguf \ | |
| --image example.png --prompt "Describe this image." \ | |
| --jinja --reasoning off -c 4096 -ngl all | |
| ``` | |
| ### 可选 MTP 推测解码 | |
| 全部主 GGUF 都包含原生 MTP 张量。兼容的 llama.cpp 版本可使用以下命令启用: | |
| ```bash | |
| llama-server -m GGUF/JoyFox-Reverie-27B-UD-Q4_K_XL.gguf \ | |
| --jinja --reasoning off -c 32768 -ngl all \ | |
| --spec-type draft-mtp --spec-draft-n-max 3 \ | |
| --host 127.0.0.1 --port 8080 | |
| ``` | |
| 这条命令替代普通服务启动命令,不需要单独下载 draft 模型。MTP 会增加显存占用,实际速度收益取决于草稿接受率与对话内容。 | |
| ### 选择量化档位 | |
| Q4 S 是本次发布中体积最小的档位。Q4 XL 可作为 RP 使用的起点,Q5、Q6 需要更多内存。可结合设备容量与实际生成效果选择。使用 GGUF 应用时,加载主文件并启用附带聊天模板;图片输入还需要配套视觉投影文件以及应用本身支持。 | |
| ## 📜 许可证与致谢 | |
| JoyFox-Reverie-27B 采用 [Apache-2.0](LICENSE) 许可证,是 JoyFox 基于 [Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) 构建的衍生模型。感谢 Qwen 团队与 Hugging Face 生态。 | |