πŸ“‹ Model Description

license: other license_name: lfm1.0 license_link: LICENSE language:
  • en
  • ja
pipeline_tag: text-generation tags:
  • liquid
  • lfm2.5
  • edge
  • llama.cpp
  • gguf
base_model:
  • LiquidAI/LFM2.5-1.2B-JP


src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png"
alt="Liquid AI"
style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
/>

Try LFM β€’
Documentation β€’
LEAP

LFM2.5-1.2B-JP

LFM2.5-JP is a Japanese language model based on the LFM2.5 hybrid architecture, optimized for Japanese text generation and completion tasks.

Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP

πŸƒ How to run

Example usage with llama.cpp:

llama-cli -hf LiquidAI/LFM2.5-1.2B-JP-GGUF --repeat_penalty 1.05

πŸ“‚ GGUF File List

πŸ“ Filename πŸ“¦ Size ⚑ Download
LFM2.5-1.2B-JP-F16.gguf
LFS FP16
2.18 GB Download
LFM2.5-1.2B-JP-Q4_0.gguf
Recommended LFS Q4
663.52 MB Download
LFM2.5-1.2B-JP-Q4_K_M.gguf
LFS Q4
697.04 MB Download
LFM2.5-1.2B-JP-Q5_K_M.gguf
LFS Q5
804.29 MB Download
LFM2.5-1.2B-JP-Q6_K.gguf
LFS Q6
918.24 MB Download
LFM2.5-1.2B-JP-Q8_0.gguf
LFS Q8
1.16 GB Download