LFM2.5-1.2B-JP

Japanese-specialized 1.2B parameter model for high-quality Japanese text generation

← Back to Text Models

LFM2.5-1.2B-JP is fine-tuned for Japanese language tasks, delivering high-quality Japanese text generation, translation, and conversation. Built on LFM2.5 with specialized Japanese training data.

HFGGUFMLXONNX

Specifications

Property	Value
Parameters	1.2B
Context Length	32K tokens
Architecture	LFM2.5 (Dense)

Japanese NLP

Native Japanese text generation

Translation

English-Japanese translation

Fine-tunable

TRL compatible (SFT, DPO, GRPO)

Quick Start

Transformers

Install:

pip install transformers torch

Download & Run:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-1.2B-JP", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-1.2B-JP")

input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": "機械学習とは何ですか？"}],
    add_generation_prompt=True, return_tensors="pt"
).to(model.device)

output = model.generate(input_ids, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))

llama.cpp

Install:

brew install llama.cpp
pip install huggingface-hub

Download:

huggingface-cli download LiquidAI/LFM2.5-1.2B-JP-GGUF \
  lfm2.5-1.2b-jp-q4_k_m.gguf --local-dir .

Run:

llama-cli -m lfm2.5-1.2b-jp-q4_k_m.gguf \
  -p "機械学習とは何ですか？" -n 256

vLLM

Install:

pip install vllm

Run:

from vllm import LLM, SamplingParams

llm = LLM(model="LiquidAI/LFM2.5-1.2B-JP")
output = llm.chat("機械学習とは何ですか？", SamplingParams(max_tokens=256))
print(output[0].outputs[0].text)