Instructions to use Maxkillor/MythTrans_llama318B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Maxkillor/MythTrans_llama318B with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Maxkillor/MythTrans_llama318B", filename="MythTrans_llama318B-unsloth.F16.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Maxkillor/MythTrans_llama318B 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 Maxkillor/MythTrans_llama318B:F16 # Run inference directly in the terminal: llama cli -hf Maxkillor/MythTrans_llama318B:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Maxkillor/MythTrans_llama318B:F16 # Run inference directly in the terminal: llama cli -hf Maxkillor/MythTrans_llama318B:F16
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 Maxkillor/MythTrans_llama318B:F16 # Run inference directly in the terminal: ./llama-cli -hf Maxkillor/MythTrans_llama318B:F16
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 Maxkillor/MythTrans_llama318B:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Maxkillor/MythTrans_llama318B:F16
Use Docker
docker model run hf.co/Maxkillor/MythTrans_llama318B:F16
- LM Studio
- Jan
- Ollama
How to use Maxkillor/MythTrans_llama318B with Ollama:
ollama run hf.co/Maxkillor/MythTrans_llama318B:F16
- Unsloth Studio
How to use Maxkillor/MythTrans_llama318B 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 Maxkillor/MythTrans_llama318B 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 Maxkillor/MythTrans_llama318B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Maxkillor/MythTrans_llama318B to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Maxkillor/MythTrans_llama318B with Docker Model Runner:
docker model run hf.co/Maxkillor/MythTrans_llama318B:F16
- Lemonade
How to use Maxkillor/MythTrans_llama318B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Maxkillor/MythTrans_llama318B:F16
Run and chat with the model
lemonade run user.MythTrans_llama318B-F16
List all available models
lemonade list
| license: cc-by-nc-4.0 | |
| tags: | |
| - unsloth | |
| - translation | |
| language: | |
| - en | |
| - zh | |
| base_model: | |
| - meta-llama/Llama-3.1-8B | |
| pipeline_tag: translation | |
| <p align="center"> | |
| <img src="./shanhaijing-banner.png" alt="Shan Hai Jing Model Banner" width="500" height="auto"> | |
| </p> | |
| # **🌟 MythTrans_llama318B 🌟** | |
| ### *Unleashing the power of AI to breathe life into mythical creatures in Classical Chinese!* | |
| This fine-tuned model, **MythTrans_llama318B**, is a celebration of the **Classic of Mountains and Seas (山海經)**—an ancient masterpiece of Chinese mythology. It is specifically designed to translate English descriptions of mythical monsters into the **elegance and depth of Classical Chinese**. Through meticulous fine-tuning with bilingual data derived from the **Classic of Mountains and Seas** and its English translations (originally from modern Chinese), this model bridges the ancient and the modern, bringing mythical beasts to life like never before. | |
| Whether you're a **researcher**, **mythology enthusiast**, or simply fascinated by the power of language, this model offers a unique way to explore and reimagine the mythical world of ancient China. | |
| This model works well on LM Studio. | |
| --- | |
| ## **✨ Key Features** | |
| - **Base Model**: *LLaMA 3.1 8B* | |
| - **Purpose**: Translating English descriptions of mythical monsters into **Classical Chinese** with literary precision and poetic beauty. | |
| - **Training Data**: A bilingual dataset from the **Classic of Mountains and Seas (山海經)** and its English translations derived from modern Chinese. | |
| - **License**: **CC BY-NC 4.0** (*Non-commercial use only, with proper attribution.*) | |
| --- | |
| ## **🔍 Why Use This Model?** | |
| - **Explore Ancient Literature**: Dive into the **rich literary heritage** of Classical Chinese with the help of AI. | |
| - **Rediscover Mythical Creatures**: Experience the mystical beasts of the **Classic of Mountains and Seas** in their original poetic glory. | |
| - **For Everyone**: Perfect for **researchers**, **language enthusiasts**, and anyone captivated by the intersection of AI and mythology. | |
| > Download this model today and let AI transport you to a world of ancient legends and mythical monsters, reimagined in the beauty of Classical Chinese! | |
| --- | |
| ## **Author:** Max Lee Tik Fan | |
| --- | |
| ## **📊 Model Comparison** | |
| - **Example 1**: | |
| Vanilla Llama 3.1 8B Output: | |
| <p align="center"> | |
| <img src="./eg1_original.png" alt="The Ember Wyrm" width="500" height="auto"> | |
| </p> | |
| MythTrans_llama318B Output: | |
| <p align="center"> | |
| <img src="./eg1_fine-tuned.png" alt="The Ember Wyrm" width="500" height="auto"> | |
| </p> | |
| - **Example 2**: | |
| Vanilla Llama 3.1 8B Output: | |
| <p align="center"> | |
| <img src="./eg2_original.png" alt="The Shadow Hag" width="500" height="auto"> | |
| </p> | |
| MythTrans_llama318B Output: | |
| <p align="center"> | |
| <img src="./eg2_fine-tuned.png" alt="The Shadow Hag" width="500" height="auto"> | |
| </p> | |
| --- | |
| # **🌏 中文介紹** | |
| ### **用人工智能的力量,將古代神話中的怪獸帶回文言文的詩意世界!** | |
| **MythTrans_llama318B** 是一款基於《**山海經**》精調的模型,專門用於將 **英文怪獸描述翻譯成典雅的文言文**。 | |
| 這款模型採用了來自《**山海經**》全文及其由現代中文翻譯成的英文文本數據,經過精心訓練,讓每一段翻譯都能展現古文的美感與文學深度,為這部傳奇古籍注入新的生命力。 | |
| 無論您是 **研究者**、**古文愛好者**,還是對怪獸傳說充滿興趣的讀者,這款模型都能為您提供探索古代神話的新方式。 | |
| 本模型在LM Studio上運行流暢。 | |
| --- | |
| ## **✨ 模型亮點** | |
| - **基礎模型**: *LLaMA 3.1 8B* | |
| - **用途**: 將 **英文怪獸描述翻譯為文言文**,保留古文的詩意與文化魅力。 | |
| - **訓練數據**: 精選自《**山海經**》全文及其由現代中文翻譯的英文版本。 | |
| - **授權許可**: **CC BY-NC 4.0** (*僅限非商業用途,需標註來源。*) | |
| --- | |
| ## **🔍 為什麼選擇這款模型?** | |
| - **探索古代文學**: 以全新的方式了解 **文言文的豐富遺產**。 | |
| - **重現神話怪獸**: 透過 AI,重新發現《**山海經**》中的 **神話怪獸**。 | |
| - **適合多種用途**: 無論是 **研究者**、**語言愛好者**,還是對 AI 與神話結合感興趣的讀者,都能從中受益。 | |
| > **立即下載這款模型**,讓人工智能帶您穿越時間,探索古老傳說中的神話世界,重現那些令人驚嘆的怪獸傳說! | |
| --- | |
| ## **作者:** Max Lee Tik Fan | |
| --- | |
| ## **📊 模型比較** | |
| - **Example 1**: | |
| 原始 Llama 3.1 8B 結果: | |
| <p align="center"> | |
| <img src="./eg1_original.png" alt="The Ember Wyrm" width="500" height="auto"> | |
| </p> | |
| MythTrans_llama318B 微調模型結果: | |
| <p align="center"> | |
| <img src="./eg1_fine-tuned.png" alt="The Ember Wyrm" width="500" height="auto"> | |
| </p> | |
| - **Example 2**: | |
| 原始 Llama 3.1 8B 結果: | |
| <p align="center"> | |
| <img src="./eg2_original.png" alt="The Shadow Hag" width="500" height="auto"> | |
| </p> | |
| MythTrans_llama318B 微調模型結果: | |
| <p align="center"> | |
| <img src="./eg2_fine-tuned.png" alt="The Shadow Hag" width="500" height="auto"> | |
| </p> | |
| --- | |
| ### **📜 License** | |
| This model is licensed under **CC BY-NC 4.0**. | |
| It is free for non-commercial use, but proper attribution is required. For full terms, visit [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/). | |
| --- | |
| ### **🛠️ Technical Details** | |
| - **Pipeline**: Translation | |
| - **Languages Supported**: English (en), Classical Chinese (zh) | |
| - **Tags**: `unsloth`, `translation`, `mythology` | |
| <p align="center"> | |
| <em>Let AI help you rediscover ancient myths and bridge cultures through the art of language!</em> | |
| </p> | |