Instructions to use MayoIsJS/trickcal_sen2epica-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use MayoIsJS/trickcal_sen2epica-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 MayoIsJS/trickcal_sen2epica-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf MayoIsJS/trickcal_sen2epica-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MayoIsJS/trickcal_sen2epica-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf MayoIsJS/trickcal_sen2epica-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 MayoIsJS/trickcal_sen2epica-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf MayoIsJS/trickcal_sen2epica-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 MayoIsJS/trickcal_sen2epica-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MayoIsJS/trickcal_sen2epica-gguf:BF16

Use Docker

docker model run hf.co/MayoIsJS/trickcal_sen2epica-gguf:BF16

Llama new
LM Studio
Jan

vLLM

How to use MayoIsJS/trickcal_sen2epica-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MayoIsJS/trickcal_sen2epica-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MayoIsJS/trickcal_sen2epica-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MayoIsJS/trickcal_sen2epica-gguf:BF16

Ollama
How to use MayoIsJS/trickcal_sen2epica-gguf with Ollama:
```
ollama run hf.co/MayoIsJS/trickcal_sen2epica-gguf:BF16
```
Unsloth Desktop
Docker Model Runner
How to use MayoIsJS/trickcal_sen2epica-gguf with Docker Model Runner:
```
docker model run hf.co/MayoIsJS/trickcal_sen2epica-gguf:BF16
```

Lemonade

How to use MayoIsJS/trickcal_sen2epica-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MayoIsJS/trickcal_sen2epica-gguf:BF16

Run and chat with the model

lemonade run user.trickcal_sen2epica-gguf-BF16

List all available models

lemonade list

Atomic Chat

해당 모델은 gguf로 변환된 모델입니다. 학습 가능한 가중치가 필요한 경우 여기를 눌러주세요.

다음 텍스트를 선비 말투로 변환: {text}<unused0>

입력된 텍스트를 에피카 말투(선비 말투)로 변환하는 모델입니다.

skt의 kogpt2-base-v2와 smilegate-ai의 korean_smile_style_dataset으로 학습된 모델입니다.

라이선스는 base 모델과 데이터셋을 따라 cc-by-nc-sa-4.0을 사용하였습니다.

주의

텍스트를 문장 단위로 잘라서 넣는 것을 추천합니다.
에피카에 특화된 데이터가 아닌 범용적인 선비 말투 데이터를 이용하였습니다.
변환 과정에서 일부 어휘가 바뀔 수 있습니다.

예시

다음 텍스트를 선비 말투로 변환: 교주님, 뒤도세요.<unused0> 교주님께선 뒤도시오!<|endoftext|>

다음 텍스트를 선비 말투로 변환: 반가워. 나는 에피카라고 해.<unused0> 고맙소! 소인은 에피카라고 하오!<|endoftext|>

Downloads last month: 10

GGUF

Model size

0.1B params

Architecture

gpt2

Hardware compatibility

16-bit

Model tree for MayoIsJS/trickcal_sen2epica-gguf

Base model

skt/kogpt2-base-v2

Finetuned

MayoIsJS/trickcal_sen2epica

Quantized

(1)

this model