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.gguf
  • exaone-4.0-1.2b-float-right-tagger.Q4_K_M.gguf โœ… 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 $'๋„ˆ๋Š” ํƒœ๊ทธ ์ƒ์„ฑ๊ธฐ๋‹ค. ๋ฐ˜๋“œ์‹œ JSON ๋ฐฐ์—ด๋งŒ ์ถœ๋ ฅํ•œ๋‹ค. ๋‹ค๋ฅธ ๊ธ€์ž ๊ธˆ์ง€.\n\
๊ทœ์น™:\n- ํƒœ๊ทธ 3~10๊ฐœ\n- ๋„ˆ๋ฌด ๋””ํ…Œ์ผํ•˜์ง€ ์•Š๊ฒŒ(ํฐ ์ฃผ์ œ)\n- ์–ธ๋”์Šค์ฝ”์–ด(_) ๊ธˆ์ง€\n\n\
๋ฌธ์žฅ:\n์ง์žฅ ์ƒ์‚ฌ๊ฐ€ ๊ณ„์† ์•ผ๊ทผ์„ ์‹œ์ผœ์„œ ์ŠคํŠธ๋ ˆ์Šค ๋ฐ›๋Š”๋‹ค. ํ‡ด์‚ฌ ๊ณ ๋ฏผ ์ค‘.\n\nassistant:\n'

Expected output (example):

["์ง์žฅ","์ŠคํŠธ๋ ˆ์Šค","ํ‡ด์‚ฌ","์ƒ์‚ฌ","์ผ์ž๋ฆฌ"]

Notes โ€ข For stricter JSON-only behavior, use --temp 0 and keep -n small (64~96).

Downloads last month
34
GGUF
Model size
1B params
Architecture
exaone4
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. ๐Ÿ™‹ Ask for provider support