Instructions to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf", filename="Gemma-4-E4B-it-Minecraft-MT-en-zh-BF16.gguf", )
llm.create_chat_completion( messages = "\"Меня зовут Вольфганг и я живу в Берлине\"" )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf 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 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16 # Run inference directly in the terminal: llama cli -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16 # Run inference directly in the terminal: llama cli -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
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 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16 # Run inference directly in the terminal: ./llama-cli -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
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 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
Use Docker
docker model run hf.co/Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
- LM Studio
- Jan
- Ollama
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf with Ollama:
ollama run hf.co/Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
- Unsloth Studio
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf 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 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf 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 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf to start chatting
- Pi
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
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 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf with Docker Model Runner:
docker model run hf.co/Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
- Lemonade
How to use Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16
Run and chat with the model
lemonade run user.Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf-BF16
List all available models
lemonade list
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 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16Run Hermes
hermesGemma4-E4B-it-Minecraft-MT-en-zh
该模型由 Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1 量化而来。
这是一个专门针对 Minecraft 及其模组以及光影生态优化的英译中机器翻译模型。
本模型基于 Gemma4 E4B 指令微调模型(Instruct)构建,通过注入大量 Minecraft 社区汉化数据,使其能够精准理解并翻译游戏内的物品描述、模组文本、光影配置,提供符合 Minecraft 玩家阅读习惯的中文翻译。
模型局限性:本模型高度垂直于 Minecraft 及其模组/光影生态。对于游戏内的专有名词、模组机制有着较高的翻译准确度;但对于非 Minecraft 领域的通用文本,其翻译质量可能不如通用的大型翻译模型。
(个人感觉4B吞吐量还是太小了准备再微调一个2B的)
微调信息
- 平台:LLaMA Factory
- GPU:Tesla V100-SXM2-16GB
| 项 | 值 |
|---|---|
| 学习率 | 7e-5 |
| 微调方法 | LoRA |
| LoRA秩 | 16 |
| LoRA缩放系数 | 32 |
| LoRA随机丢弃 | 0.05 |
| 预热步数 | 150 |
| 批处理大小 | 2 |
| 梯度累计 | 6 |
| 计算类型 | pure_bf16 |
| 量化方法 | bnb |
| 量化等级 | 4 |
| 对话模板 | gemma4n |
| 结束时Epoch | ~0.245 |
| 结束时耗时 | ~64.5小时 |
⚠️ 许可证与严格使用限制 (License & Restrictions)
🚨 本模型及其权重严禁用于任何商业目的! 🚨
本模型的最终发布许可证为 CC BY-NC-SA 4.0。
- ✅ 允许:个人学习、学术研究、非盈利性质的开源项目、个人整合包内部使用。
- ❌ 禁止:任何形式的商业使用(包括但不限于:集成到收费软件/游戏中、用于商业 API 服务、作为商业产品的内部组件、用于盈利的网站或服务器等)。
- 🔄 要求:如果您修改或基于本模型进行二次微调,您的衍生模型必须同样采用 CC BY-NC-SA 4.0 协议发布。
为什么本模型不能商用?
虽然本模型的基础架构(Base Model)允许一定程度的自由使用,但本模型在微调/训练过程中使用了受 CC BY-NC-SA 4.0 协议严格保护的数据集。根据衍生作品的协议继承原则,最终发布的模型必须遵守数据集中“禁止商用 (Non-Commercial)”和“相同方式共享 (ShareAlike)”的限制。
📜 基础模型与数据来源 (Attribution)
基础模型 (Base Model)
本模型基于以下开源模型进行微调:
- 基础模型: google/gemma-4-E4B-it
- 基础模型协议: Apache 2.0
训练数据集 (Training Data)
本模型的翻译能力离不开 Minecraft 社区汉化者的无私奉献。训练数据主要来源于以下项目,在此向所有译者致以最崇高的敬意!
- CFPA 模组汉词典 (i18n-dict)
- 仓库: CFPATools/i18n-dict
- 协议: CC BY-NC-SA 4.0
- Minecraft 光影中文本地化 (Minecraft-Shaders-zh_CN-Lang-Files)
- 仓库: NakiriRuri/Minecraft-Shaders-zh_CN-Lang-Files
- 协议: CC BY-NC-SA 4.0
注:本模型严格遵守上述数据集的 CC BY-NC-SA 4.0 协议条款。
- Downloads last month
- 711
8-bit
16-bit
Model tree for Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf
Base model
google/gemma-4-E4B
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp# Start a local OpenAI-compatible server: llama serve -hf Q1ngMang/Gemma-4-E4B-it-Minecraft-MT-en-zh-v0.1-gguf:BF16