Text Generation
Transformers
Safetensors
GGUF
Korean
gemma4
image-text-to-text
gemma
korean
roleplay
mud
lore
llama.cpp
lmstudio
conversational
Instructions to use sangwon1472/gemma4-e2b-mud with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sangwon1472/gemma4-e2b-mud with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sangwon1472/gemma4-e2b-mud") 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)# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("sangwon1472/gemma4-e2b-mud") model = AutoModelForImageTextToText.from_pretrained("sangwon1472/gemma4-e2b-mud") 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=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - llama-cpp-python
How to use sangwon1472/gemma4-e2b-mud with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="sangwon1472/gemma4-e2b-mud", filename="gemma4-e2b-mud-Q4_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use sangwon1472/gemma4-e2b-mud with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf sangwon1472/gemma4-e2b-mud:UD-Q4_K_M # Run inference directly in the terminal: llama-cli -hf sangwon1472/gemma4-e2b-mud:UD-Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf sangwon1472/gemma4-e2b-mud:UD-Q4_K_M # Run inference directly in the terminal: llama-cli -hf sangwon1472/gemma4-e2b-mud: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 sangwon1472/gemma4-e2b-mud:UD-Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf sangwon1472/gemma4-e2b-mud: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 sangwon1472/gemma4-e2b-mud:UD-Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf sangwon1472/gemma4-e2b-mud:UD-Q4_K_M
Use Docker
docker model run hf.co/sangwon1472/gemma4-e2b-mud:UD-Q4_K_M
- LM Studio
- Jan
- vLLM
How to use sangwon1472/gemma4-e2b-mud with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sangwon1472/gemma4-e2b-mud" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sangwon1472/gemma4-e2b-mud", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/sangwon1472/gemma4-e2b-mud:UD-Q4_K_M
- SGLang
How to use sangwon1472/gemma4-e2b-mud 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 "sangwon1472/gemma4-e2b-mud" \ --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": "sangwon1472/gemma4-e2b-mud", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "sangwon1472/gemma4-e2b-mud" \ --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": "sangwon1472/gemma4-e2b-mud", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use sangwon1472/gemma4-e2b-mud with Ollama:
ollama run hf.co/sangwon1472/gemma4-e2b-mud:UD-Q4_K_M
- Unsloth Studio new
How to use sangwon1472/gemma4-e2b-mud 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 sangwon1472/gemma4-e2b-mud 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 sangwon1472/gemma4-e2b-mud to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for sangwon1472/gemma4-e2b-mud to start chatting
- Docker Model Runner
How to use sangwon1472/gemma4-e2b-mud with Docker Model Runner:
docker model run hf.co/sangwon1472/gemma4-e2b-mud:UD-Q4_K_M
- Lemonade
How to use sangwon1472/gemma4-e2b-mud with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sangwon1472/gemma4-e2b-mud:UD-Q4_K_M
Run and chat with the model
lemonade run user.gemma4-e2b-mud-UD-Q4_K_M
List all available models
lemonade list
| license: apache-2.0 | |
| language: | |
| - ko | |
| library_name: transformers | |
| pipeline_tag: text-generation | |
| base_model: | |
| - google/gemma-4-E2B-it | |
| tags: | |
| - gemma | |
| - gemma4 | |
| - korean | |
| - roleplay | |
| - mud | |
| - lore | |
| - gguf | |
| - llama.cpp | |
| - lmstudio | |
| - transformers | |
| # gemma4-e2b-mud | |
| `gemma4-e2b-mud` λ **Gemma 4 E2B κ³μ΄μ κΈ°λ°μΌλ‘ ν νκ΅μ΄ μ°μ£Όνν ν μ€νΈ MUD μ€νμΌ λͺ¨λΈ**μ΄λ€. | |
| μ§§μ λͺ λ Ή λ°μ, NPC λμ¬, λ°© λΆμκΈ° λ¬μ¬, μ μΉ μ€λͺ , νλ‘ ννΈ κ°μ **κ²μ μμ¬ λ μ΄μ΄**λ₯Ό λ€λ£¨κΈ° μ’κ² μ 리ν 체ν¬ν¬μΈνΈμ, μ΄λ₯Ό μ¬ννκ±°λ νμ₯ν μ μλ **Colab μ€νν° ν¨ν€μ§**, κ·Έλ¦¬κ³ **LM Studioμ© GGUF**λ₯Ό ν¨κ» μ 곡νλ€. | |
| μ΄ μ μ₯μμ ν΅μ¬ λ°©ν₯μ βκ²μ μμ§μ νμ βμ΄ μλλΌ, **λ§ν¬, λΆμκΈ°, μ§§μ μΈκ³κ΄ μλ΅**μ AIκ° λ§‘λλ‘ λ§λλ κ²μ΄λ€. | |
| ## TL;DR | |
| - κΈ°λ° λͺ¨λΈ: `google/gemma-4-E2B-it` | |
| - μ£Ό μ¬μ© μΈμ΄: νκ΅μ΄ | |
| - μ£Ό μ¬μ© μμ: ν μ€νΈ MUD, NPC λν, λ£Έ λ¬μ¬, μ μΉ/λ‘μ΄ μ€λͺ | |
| - ν¬ν¨ νμ: | |
| - Transformers 체ν¬ν¬μΈνΈ | |
| - LM Studio / llama.cpp μ© `GGUF` | |
| - Colab / Unsloth μ¬νμ© μ€νν° ν¨ν€μ§ | |
| - κ°μ₯ μ λ§λ μ λ ₯: | |
| - `talk oracle` | |
| - `look` | |
| - `rumor` | |
| - `scan signal` | |
| - `First Fire Horizonμ΄ μ΄λ€ κ³³μΈμ§ μ€λͺ ν΄μ€.` | |
| ## μ΄ μ μ₯μμ λ€μ΄ μλ κ² | |
| ### 1. Transformers 체ν¬ν¬μΈνΈ | |
| 루νΈμλ λ³ν©λ Hugging Face νμ λͺ¨λΈ κ°μ€μΉκ° λ€μ΄ μλ€. | |
| - `model-00001-of-00005.safetensors` | |
| - `model-00002-of-00005.safetensors` | |
| - `model-00003-of-00005.safetensors` | |
| - `model-00004-of-00005.safetensors` | |
| - `model-00005-of-00005.safetensors` | |
| - `config.json` | |
| - `processor_config.json` | |
| - `tokenizer.json` | |
| - `tokenizer_config.json` | |
| - `chat_template.jinja` | |
| ### 2. GGUF | |
| LM Studio / llama.cpp μ λ°λ‘ κ°μ Έκ° μ μλλ‘ λ€μ GGUF νμΌμ ν¨κ» μ 곡νλ€. | |
| - `gemma4-e2b-mud-Q4_K_M.gguf` | |
| μ΄ νμΌμ λ‘컬 μΆλ‘ , LM Studio ν μ€νΈ, λΉ λ₯Έ λ°°ν¬μ μ ν©ν μμμ μ΄λ€. | |
| ### 3. Companion starter package | |
| μ μ₯μ μμ [`gemma-mud-colab-starter/`](./gemma-mud-colab-starter) ν΄λμλ λ€μμ΄ ν¬ν¨λμ΄ μλ€. | |
| - Colab λ ΈνΈλΆ | |
| - E2B / E4B μ€νμ© λ ΈνΈλΆ λ³ν | |
| - μμ λ°μ΄ν°μ | |
| - LM Studio μμ€ν ν둬ννΈ | |
| - ν μ€νΈ ν둬ννΈ | |
| - μ€ν μλ΄μ νΈλ¬λΈμν λ¬Έμ | |
| μ¦ μ΄ μ μ₯μλ βλͺ¨λΈλ§ λμ Έ λμ ννβκ° μλλΌ, **μ€νκ³Ό λ°°ν¬κΉμ§ μ΄μ΄μ§λ ν¨ν€μ§ν μ μ₯μ**λ₯Ό λͺ©νλ‘ νλ€. | |
| λ°μ΄ν°μ ꡬ쑰μ μ μ λ°©λ²μ λ³λ λ¬Έμμ μ λ¦¬ν΄ λμλ€. | |
| - [`DATASET_GUIDE.md`](./DATASET_GUIDE.md) | |
| ## λͺ¨λΈ κ°μ | |
| μ΄ λͺ¨λΈμ **Gemma 4 E2B instruct κ³μ΄μ ν μ€νΈ MUD ν€μ λ§κ² λ€λ¬μ νμ λͺ¨λΈ**μ΄λ€. | |
| μ§ν₯νλ μλ΅μ μλμ κ°λ€. | |
| - μ§§κ³ μ λͺ ν NPC λμ¬ | |
| - λΆμκΈ°κ° μ΄μ μλ λ°©/μ₯λ©΄ μ€λͺ | |
| - μΈκ³κ΄ κ³ μ λͺ μ¬λ₯Ό μ€μ¬μΌλ‘ ν μ μΉ/λ‘μ΄ μλ΄ | |
| - νλ μ΄λ₯Ό λλ μ§§μ ννΈ | |
| - λ²μ© λΉμν λ΅λ³λ³΄λ€, **μΈκ³ μμ 머무λ₯΄λ λ°μ** | |
| λ°λλ‘ μλμ κ°μ λ°©ν₯μ νΌνλλ‘ μ€κ³νλ€. | |
| - νμ€ κΈ°μ /DB/μμ μ€λͺ μΌλ‘ μλ λ΅λ³ | |
| - `AIλ‘μ...` κ°μ λ©ν λ°μΈ | |
| - μ₯ν©ν λ°±κ³Όμ¬μ μ μ€λͺ | |
| - κ²μ μνλ₯Ό λͺ¨λΈμ΄ μμλ‘ νμ νλ λ°ν | |
| ## κΈ°λ° λͺ¨λΈκ³Ό ꡬ쑰 | |
| μ΄ μ μ₯μμ κΈ°λ°μ [`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it) μ΄λ€. | |
| Gemma 4 E2Bλ Googleμ μμ Gemma 4 κ³μ΄ λͺ¨λΈμ΄λ©°, 곡μ μΉ΄λ κΈ°μ€μΌλ‘ **Apache 2.0** λΌμ΄μ μ€λ₯Ό μ¬μ©νλ€. | |
| μ£Όμ: | |
| - **μ΄ μ μ₯μ 루νΈμ μ¬λΌμ¨ μ€μ κ°μ€μΉμ GGUFλ E2B κΈ°λ°μ΄λ€.** | |
| - starter package μμ λ€μ΄ μλ `E4B` λ ΈνΈλΆμ **E4B μ€ν/μ¬νμ΅μ© companion notebook** μ΄λ©°, λ£¨νΈ μ²΄ν¬ν¬μΈνΈκ° E4BλΌλ λ»μ μλλ€. | |
| μ΄ μ μ₯μμ λ‘컬 `config.json` κΈ°μ€ μ£Όμ ν μ€νΈ μ€μ μ λ€μκ³Ό κ°λ€. | |
| - μν€ν μ²: `Gemma4ForConditionalGeneration` | |
| - `model_type`: `gemma4` | |
| - ν μ€νΈ hidden size: `1536` | |
| - ν μ€νΈ λ μ΄μ΄ μ: `35` | |
| - attention heads: `8` | |
| - key/value heads: `1` | |
| - intermediate size: `6144` | |
| - vocab size: `262144` | |
| - sliding window: `512` | |
| μ€μ: | |
| - **μ΄ νμ λͺ¨λΈμ μ€μ μ¬μ© μ΄μ μ ν μ€νΈ μμ±**μ΄λ€. | |
| - Gemma 4 E2B κ³μ΄ μ체λ μμ λ©ν°λͺ¨λ¬ κ³μ΄μ΄μ§λ§, μ΄ μ μ₯μμ μ€νν° ν¨ν€μ§μ μμ ν둬ννΈλ **ν μ€νΈ MUD μ¬μ© μλ리μ€**μ λ§μΆ°μ Έ μλ€. | |
| - ν¨κ» λ€μ΄ μλ GGUF νμΌ μμ LM Studioμμ **ν μ€νΈ λν μ€μ¬**μΌλ‘ λ°λ‘ ν μ€νΈνλ μ©λμ λ§λ€. | |
| ## μ΄λ€ μμ μ μ λ§λκ° | |
| ### μ λ§λ μμ | |
| - ν μ€νΈ MUD NPC λν | |
| - λ£Έ/μ₯λ©΄ λΆμκΈ° λ¬μ¬ | |
| - μ§§μ rumor / lore / signal μλ΅ | |
| - λ‘컬 μ€ν 리ν λ§ ν μ€νΈ | |
| - νκ΅μ΄ μΈκ³κ΄ νλ‘ν νμ΄ν | |
| - MUD μμ§μ βμμ¬ λ μ΄μ΄β λΆλ¦¬ μ€ν | |
| ### νΉν μ λ§λ μ λ ₯ μ€νμΌ | |
| - νλ λ¨μ΄ λͺ λ Ήν | |
| - `talk oracle` | |
| - `look` | |
| - `rumor` | |
| - `scan signal` | |
| - μ§§μ μ€λͺ μμ²ν | |
| - `First Fire Horizonμ΄ μ΄λ€ κ³³μΈμ§ μ€λͺ ν΄μ€.` | |
| - `Helios Vergeμ μλ―Έμ μ€μμ±μ μ€λͺ ν΄μ€.` | |
| ## μ΄λ€ μμ μλ λ§μ§ μλκ° | |
| μ΄ λͺ¨λΈμ μλ μν μ **μ§μ λ΄λΉνμ§ μλ νΈμ΄ μμ νλ€.** | |
| - νμ€νΈ μλ£ νμ | |
| - 보μ μ§κΈ | |
| - μμ΄ν /골λ μ μ° | |
| - λ¬Έ μ΄λ¦Ό/μ κΈ λ± μν λ³κ²½ νμ | |
| - μ ν¬ μΉν¨ κ³μ° | |
| - λ²λ₯ , μλ£, κΈμ΅ κ°μ κ³ μ λ’° μ 보 μ 곡 | |
| μ¦, μΆμ² μ¬μ© ꡬ쑰λ λ€μκ³Ό κ°λ€. | |
| - **μμ§**: μ΄λ, μ ν¬, μν, 보μ, νμ€νΈ λ‘μ§ | |
| - **λͺ¨λΈ**: λμ¬, λΆμκΈ°, μ μΉ, μ§§μ ννΈ, λ¬μ¬ | |
| ## λΉ λ₯Έ μμ | |
| ### Transformers λ‘ λ°λ‘ μ°κΈ° | |
| Gemma 4 곡μ λ¬Έμμ μ¬μ© λ°©μμ λ§μΆ° `AutoProcessor` + `AutoModelForImageTextToText` κ²½λ‘λ‘ μμν μ μλ€. | |
| ```python | |
| from transformers import AutoProcessor, AutoModelForImageTextToText | |
| import torch | |
| MODEL_ID = "sangwon1472/gemma4-e2b-mud" | |
| processor = AutoProcessor.from_pretrained(MODEL_ID) | |
| model = AutoModelForImageTextToText.from_pretrained( | |
| MODEL_ID, | |
| dtype="auto", | |
| device_map="auto", | |
| ) | |
| messages = [ | |
| { | |
| "role": "system", | |
| "content": "λΉμ μ μ°μ£Όνν ν μ€νΈ MUDμ νλ‘ μλ΄μμ΄μ μΈκ³κ΄ ν΄μ€μλ€. λ΅λ³μ νκ΅μ΄λ‘ νλ€." | |
| }, | |
| { | |
| "role": "user", | |
| "content": "talk oracle" | |
| }, | |
| ] | |
| text = processor.apply_chat_template( | |
| messages, | |
| tokenize=False, | |
| add_generation_prompt=True, | |
| enable_thinking=False, | |
| ) | |
| inputs = processor(text=text, return_tensors="pt").to(model.device) | |
| input_len = inputs["input_ids"].shape[-1] | |
| with torch.no_grad(): | |
| outputs = model.generate( | |
| **inputs, | |
| max_new_tokens=128, | |
| temperature=1.0, | |
| top_p=0.95, | |
| top_k=64, | |
| ) | |
| response = processor.decode(outputs[0][input_len:], skip_special_tokens=False) | |
| print(processor.parse_response(response)) | |
| ``` | |
| ## LM Studio / llama.cpp μ¬μ© | |
| μ΄ μ μ₯μμλ λ°λ‘ import κ°λ₯ν GGUF νμΌμ΄ ν¬ν¨λμ΄ μλ€. | |
| - `gemma4-e2b-mud-Q4_K_M.gguf` | |
| LM Studio μμλ μ΄ GGUFλ₯Ό κ°μ Έμμ λ°λ‘ ν μ€νΈν μ μλ€. | |
| ν¨κ» μ 곡νλ μμ€ν ν둬ννΈμ ν μ€νΈ λ¬Έμ₯μ starter package μμ μλ€. | |
| - [`lmstudio_system_prompt_ko.txt`](./gemma-mud-colab-starter/examples/lmstudio_system_prompt_ko.txt) | |
| - [`lmstudio_system_prompt_npc_ko.txt`](./gemma-mud-colab-starter/examples/lmstudio_system_prompt_npc_ko.txt) | |
| - [`lmstudio_system_prompt_lore_ko.txt`](./gemma-mud-colab-starter/examples/lmstudio_system_prompt_lore_ko.txt) | |
| - [`lmstudio_test_prompts.md`](./gemma-mud-colab-starter/examples/lmstudio_test_prompts.md) | |
| ### κΆμ₯ μμ ν둬ννΈ | |
| - `talk oracle` | |
| - `look` | |
| - `rumor` | |
| - `scan signal` | |
| - `First Fire Horizonμ΄ μ΄λ€ κ³³μΈμ§ μ€λͺ ν΄μ€.` | |
| ### κΆμ₯ μμ± μ€μ | |
| Gemma 4 κ³μ΄μ 곡μ/μ€μ μ¬μ©μμ μλ κ°μ΄ 무λν μΆλ°μ μ΄λ€. | |
| - `temperature = 1.0` | |
| - `top_p = 0.95` | |
| - `top_k = 64` | |
| λ³΄λ€ μ§§κ³ μμ μ μΈ NPC λ΅λ³μ΄ νμνλ©΄ μλμ²λΌ μ‘°κΈ λ³΄μμ μΌλ‘ μμν΄λ μ’λ€. | |
| - `temperature = 0.7` | |
| - `max tokens = 96 ~ 128` | |
| μμ βλ μ§§κ²β μ€μ μ μ΄ μ μ₯μμ MUD μ©λμ λ§μΆ μ€μ κΆμ₯κ°μ΄λ€. | |
| ## Companion starter package μλ΄ | |
| ν¨κ» μ 곡νλ [`gemma-mud-colab-starter/`](./gemma-mud-colab-starter) ν΄λλ λͺ¨λΈμ λ€μ νμ΅νκ±°λ λ³νν΄ λ³΄κ³ μΆμ μ¬μ©μλ₯Ό μν ꡬμ±μ΄λ€. | |
| μ£Όμ νμΌ: | |
| - [`README.md`](./gemma-mud-colab-starter/README.md) | |
| - [`run_instructions.md`](./gemma-mud-colab-starter/run_instructions.md) | |
| - [`troubleshooting.md`](./gemma-mud-colab-starter/troubleshooting.md) | |
| - [`Gemma4_MUD_QLoRA_Colab_Notebook-E2B.ipynb`](./gemma-mud-colab-starter/notebooks/Gemma4_MUD_QLoRA_Colab_Notebook-E2B.ipynb) | |
| - [`Gemma4_MUD_QLoRA_Colab_Notebook-E4B.ipynb`](./gemma-mud-colab-starter/notebooks/Gemma4_MUD_QLoRA_Colab_Notebook-E4B.ipynb) | |
| ν¬ν¨λ μμ λ°μ΄ν°μ : | |
| - `combined_1000.jsonl` : 1000ν μλ³Έ | |
| - `combined_1000.unsloth_chatml_dedup.jsonl` : 963ν μ 리본 | |
| - `combined_1000.unsloth_gemma4_messages_dedup.jsonl` : 963ν Gemma 4 messages μ 리본 | |
| - `gemma4_mud_alpaca_100.jsonl` : 100ν μν μμ | |
| λ°μ΄ν°μ μ ꡬ쑰, λΆν¬, μ μ λ°©μ, μ μν μμ± κ·μΉμ λ³λ λ¬Έμμμ μμΈν λ€λ£¬λ€. | |
| - [`DATASET_GUIDE.md`](./DATASET_GUIDE.md) | |
| μ€μ: | |
| - μ λ°μ΄ν°μ μ **starter/retraining/example μ©λ**λ‘ ν¨κ» λ£μ΄ λ κ²μ΄λ€. | |
| - μ΄ μ μ₯μμ 체ν¬ν¬μΈνΈλ₯Ό μ΄ν΄νκ±°λ νμ₯νλ λ° λμμ μ£Όλ μλ£μ΄λ©°, μ¬ν μ€νμ μν μΆλ°μ μΌλ‘ 보λ νΈμ΄ μ’λ€. | |
| ## μλ΅ νμ§μ λ³Ό λ μ’μ κΈ°μ€ | |
| μ λ΅ λ¬Έμ₯μ μΈμ λ΄λμ§κ° ν΅μ¬μ μλλ€. | |
| λ μ€μν κ²μ **μλ΅μ κ²°**μ΄λ€. | |
| μ’μ μ νΈ: | |
| - νκ΅μ΄λ‘ λ΅νλ€ | |
| - μΈκ³κ΄ μμ λ¨Έλ¬Έλ€ | |
| - μ§§κ³ λΆμκΈ°κ° μλ€ | |
| - λͺ λ Ήμ΄λ³ λ°μ κ²°μ΄ λ€λ₯΄λ€ | |
| - νμ€ μΌλ° μμ κ°μλ‘ μμ§ μλλ€ | |
| κ²½κ³ μ νΈ: | |
| - `Hello!` λ‘ μμνλ λ²μ© μ±λ΄ ν€ | |
| - `Oracle Database` κ°μ νμ€ μμ λ°μ | |
| - `AIλ‘μ` κ°μ λ©ν λ°μΈ | |
| - μμ§μ΄ ν΄μΌ ν μν νμ μ λͺ¨λΈμ΄ μ§μ μ μΈ | |
| ## νκ³μ μ£Όμμ¬ν | |
| μ΄ λͺ¨λΈμ νΉμ μ€νμΌκ³Ό μ©λμ λ§μΆ **λλ©μΈ μ μν λͺ¨λΈ**μ΄λ€. λ°λΌμ μλ νκ³λ₯Ό μ΄ν΄νκ³ μ°λ κ²μ΄ μ’λ€. | |
| - μΈκ³κ΄ ν€μ κ°νλμ§λ§, μμ λλ©μΈ μ μ λͺ¨λΈ νΉμ±μ **κ³ μ λͺ μ¬λ₯Ό κ³Όμ₯λκ² μ΄μ΄λΆμ΄κ±°λ λΆμκΈ°λ₯Ό κ³Όμμ±**ν μ μλ€. | |
| - ν μ€νΈ MUD μμ¬μλ μ λ§μ§λ§, μΌλ° λΉμν μ§μμλ΅μ μ νλλ₯Ό λͺ©νλ‘ νμ§λ μμλ€. | |
| - μ₯ν©ν μ€λͺ μ μ€μ΄κΈ° μν΄ ν둬ννΈμ μμ€ν λ©μμ§λ₯Ό μ§§κ³ λͺ ννκ² μ μ§νλ νΈμ΄ μ’λ€. | |
| - 곡μ λ²€μΉλ§ν¬ κΈ°λ° μ¬νκ°λ λ³λ μμ μ± νκ°λ₯Ό μ΄ μΉ΄λμμ μ 곡νμ§λ μλλ€. | |
| ## κΆμ₯ μ¬μ© ν¨ν΄ | |
| μ΄ λͺ¨λΈμ μλμ²λΌ λΆμ΄λ©΄ κ°μ₯ μμ°μ€λ½λ€. | |
| 1. νλ μ΄μ΄ μ λ ₯μ μ§§μ ν μ€νΈ ν둬ννΈλ‘ μ 리νλ€. | |
| 2. μμ§μ μν/νμ μ μ²λ¦¬νλ€. | |
| 3. λͺ¨λΈμ λμ¬, λ¬μ¬, ννΈ, μ μΉ μ€λͺ μ μμ±νλ€. | |
| 4. μμ§μ λͺ¨λΈ μΆλ ₯μ κ·Έλλ‘ μ°κΈ°λ³΄λ€, νμνλ©΄ νμ²λ¦¬ κ·μΉμ λλ€. | |
| νΉν μλ μ μ μ§ν€λ νΈμ΄ μ’λ€. | |
| - **μμ§μ΄ κ²°μ ν΄μΌ ν κ²**: νμ€νΈ μ±κ³΅, 보μ, μ ν¬ νμ , λ¬Έ μν | |
| - **λͺ¨λΈμ΄ ννν΄λ μ’μ κ²**: λΆμκΈ°, λͺ©μ리, μ¬μ΄, λ¨μ, λ¬Έν, μ ν | |
| ## λΌμ΄μ μ€μ μΆμ² | |
| - νμ κΈ°λ° λͺ¨λΈ: [`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it) | |
| - λΌμ΄μ μ€ νκΈ°: `Apache-2.0` | |
| - GGUF λ° starter package λ μ΄ μ μ₯μ λ°°ν¬ νΈμλ₯Ό μν΄ ν¨κ» ν¬ν¨νλ€. | |
| Gemma 4 μ체μ ꡬ쑰μ κΈ°λ³Έ μ¬μ© λ°©μμ 곡μ Gemma 4 μΉ΄λμ Unsloth Gemma 4 λ¬Έμλ₯Ό μ°Έκ³ νλ©΄ μ’λ€. | |
| - [Google Gemma 4 E2B model card](https://huggingface.co/google/gemma-4-E2B-it) | |
| - [Unsloth Gemma 4 docs](https://unsloth.ai/docs/models/gemma-4) | |
| ## ν μ€ μμ½ | |
| `gemma4-e2b-mud` λ **νκ΅μ΄ μ°μ£Όνν ν μ€νΈ MUDμ λΆμκΈ°, NPC λμ¬, μ μΉ μ€λͺ μ λ‘컬μμλ λΉ λ₯΄κ² μνν μ μκ² λ§λ Gemma 4 E2B νμ λͺ¨λΈ + GGUF + Colab starter package λ¬Άμ**μ΄λ€. | |