Text Generation
Safetensors
GGUF
Chinese
English
qwen3
fortune-telling
qwen
qwen2.5
ollama
conversational
Instructions to use Tbata7/FortuneQwen3_4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Tbata7/FortuneQwen3_4b 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 Tbata7/FortuneQwen3_4b:Q8_0 # Run inference directly in the terminal: llama cli -hf Tbata7/FortuneQwen3_4b:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Tbata7/FortuneQwen3_4b:Q8_0 # Run inference directly in the terminal: llama cli -hf Tbata7/FortuneQwen3_4b:Q8_0
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 Tbata7/FortuneQwen3_4b:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf Tbata7/FortuneQwen3_4b:Q8_0
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 Tbata7/FortuneQwen3_4b:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Tbata7/FortuneQwen3_4b:Q8_0
Use Docker
docker model run hf.co/Tbata7/FortuneQwen3_4b:Q8_0
- LM Studio
- Jan
- vLLM
How to use Tbata7/FortuneQwen3_4b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Tbata7/FortuneQwen3_4b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Tbata7/FortuneQwen3_4b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Tbata7/FortuneQwen3_4b:Q8_0
- Ollama
How to use Tbata7/FortuneQwen3_4b with Ollama:
ollama run hf.co/Tbata7/FortuneQwen3_4b:Q8_0
- Unsloth Studio
How to use Tbata7/FortuneQwen3_4b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Tbata7/FortuneQwen3_4b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Tbata7/FortuneQwen3_4b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Tbata7/FortuneQwen3_4b to start chatting
- Docker Model Runner
How to use Tbata7/FortuneQwen3_4b with Docker Model Runner:
docker model run hf.co/Tbata7/FortuneQwen3_4b:Q8_0
- Lemonade
How to use Tbata7/FortuneQwen3_4b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Tbata7/FortuneQwen3_4b:Q8_0
Run and chat with the model
lemonade run user.FortuneQwen3_4b-Q8_0
List all available models
lemonade list
- Atomic Chat
| license: other | |
| language: | |
| - zh | |
| - en | |
| pipeline_tag: text-generation | |
| tags: | |
| - fortune-telling | |
| - qwen | |
| - qwen2.5 | |
| - qwen3 | |
| - gguf | |
| - ollama | |
| <div align="center"> | |
| # FortuneQwen3_4b | |
| [**中文**](./README.md) | [**English**](./README_EN.md) | |
| </div> | |
| 这是一个基于 Qwen3 架构微调的 4B 参数模型,专门用于算命/占卜(Fortune Telling)任务。本仓库同时提供了合并后的 Safetensors 权重、GGUF 量化文件以及 Ollama 使用的 Modelfile。 | |
| ## 关于本仓库 (About This Repository) | |
| 本仓库包含以下三种格式的模型文件,您可以根据需要选择使用: | |
| 1. **GGUF 量化模型 (Recommended)**: | |
| * 文件名: `FortuneQwen3_4b_q8_0.gguf` (或其他量化版本) | |
| * 说明: 已经预先转换好的 GGUF 格式 (Int8 量化),可直接用于 `llama.cpp` 或 `Ollama`。 | |
| 2. **Modelfile**: | |
| * 文件名: `Modelfile` | |
| * 说明: 用于导入 Ollama 的配置文件,定义了系统提示词和参数。 | |
| 3. **Hugging Face Safetensors**: | |
| * 文件名: `model.safetensors` 等 | |
| * 说明: 已经合并了 LoRA 权重的完整模型参数,适用于基于 Transformers 的推理或进一步微调,也可以用于导出自定义的 GGUF。 | |
| ## 快速使用 (Quick Start) | |
| ### 选项 1: 使用 Ollama (推荐) | |
| 您可以使用本仓库中已经转换好的 GGUF 文件快速创建 Ollama 模型。 | |
| 1. **克隆本仓库**: | |
| ```bash | |
| git clone https://huggingface.co/Tbata7/FortuneQwen3_4b | |
| cd FortuneQwen3_4b | |
| ``` | |
| 2. **创建模型**: | |
| ```bash | |
| # 这一步会使用目录下的 Modelfile 和 GGUF 文件 | |
| ollama create FortuneQwen3_q8:4b -f Modelfile | |
| ``` | |
| 3. **运行模型**: | |
| ```bash | |
| ollama run FortuneQwen3_q8:4b | |
| ``` | |
| ### 选项 2: 使用 llama.cpp | |
| 如果您想直接使用 GGUF 文件: | |
| ```bash | |
| ./llama-cli -m FortuneQwen3_4b_q8_0.gguf -p "你的占卜问题..." -n 512 | |
| ``` | |
| ## 高级用法:导出自定义 GGUF (Advanced Usage) | |
| 如果您希望使用不同的量化精度(如 q4_k, q6_k, fp16 等),可以使用 `llama.cpp` 自行从 Safetensors 权重导出。 | |
| 1. **准备环境**: | |
| 确保您已经安装了 `llama.cpp` 的 python 依赖。 | |
| 2. **转换模型**: | |
| 使用 `convert_hf_to_gguf.py` 脚本进行转换。您需要指定 `--outtype` 参数来控制输出类型。 | |
| * **导出为 FP16 (不量化)**: | |
| ```bash | |
| python llama.cpp/convert_hf_to_gguf.py ./FortuneQwen3_4b --outfile FortuneQwen3_4b_fp16.gguf --outtype f16 | |
| ``` | |
| * **导出为 Int8 (q8_0)**: | |
| ```bash | |
| python llama.cpp/convert_hf_to_gguf.py ./FortuneQwen3_4b --outfile FortuneQwen3_4b_q8_0.gguf --outtype q8_0 | |
| ``` | |
| * **其他量化**: | |
| 您可以先导出为 f16,然后使用 `llama-quantize` 工具进一步量化: | |
| ```bash | |
| ./llama-quantize FortuneQwen3_4b_fp16.gguf FortuneQwen3_4b_q4_k_m.gguf q4_k_m | |
| ``` | |
| ## 模型信息 (Model Information) | |
| - **基础架构 (Base Architecture)**: Qwen3:4B | |
| - **任务 (Task)**: 算命 / 占卜 / 易经解读 | |
| - **上下文长度 (Context Window)**: 32768 | |
| - **微调框架**: LLaMA-Factory | |
| ## 声明 | |
| 本模型仅供娱乐和研究使用,算命结果仅供参考,请相信科学。 | |