EXAONE-4.0-1.2B Float:Right Tagger (GGUF)
GGUF builds for EXAONE-4.0-1.2B Float:Right Tagger.
This model is tuned to output tags as a JSON array for short Korean text inputs.
non-GGUF : https://huggingface.co/FloatDo/exaone-4.0-1.2b-float-right-tagger
Files
exaone-4.0-1.2b-float-right-tagger.f16.gguf(FP16)exaone-4.0-1.2b-float-right-tagger.Q8_0.ggufexaone-4.0-1.2b-float-right-tagger.Q4_K_M.ggufโ recommended (often outputs clean tags with less extra text)
Prompt format (llama.cpp)
Example:
llama-cli -m exaone-4.0-1.2b-float-right-tagger.Q4_K_M.gguf -n 96 -t 8 --temp 0 \
-p $'๋๋ ํ๊ทธ ์์ฑ๊ธฐ๋ค. ๋ฐ๋์ JSON ๋ฐฐ์ด๋ง ์ถ๋ ฅํ๋ค. ๋ค๋ฅธ ๊ธ์ ๊ธ์ง.\n\
๊ท์น:\n- ํ๊ทธ 3~10๊ฐ\n- ๋๋ฌด ๋ํ
์ผํ์ง ์๊ฒ(ํฐ ์ฃผ์ )\n- ์ธ๋์ค์ฝ์ด(_) ๊ธ์ง\n\n\
๋ฌธ์ฅ:\n์ง์ฅ ์์ฌ๊ฐ ๊ณ์ ์ผ๊ทผ์ ์์ผ์ ์คํธ๋ ์ค ๋ฐ๋๋ค. ํด์ฌ ๊ณ ๋ฏผ ์ค.\n\nassistant:\n'
Expected output (example):
["์ง์ฅ","์คํธ๋ ์ค","ํด์ฌ","์์ฌ","์ผ์๋ฆฌ"]
Notes โข For stricter JSON-only behavior, use --temp 0 and keep -n small (64~96).
- Downloads last month
- 34
Hardware compatibility
Log In to add your hardware
4-bit
8-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support