license, language, programming_language, pipeline_tag, library_name, inference, base_model, tags

license	language	programming_language	pipeline_tag	library_name	inference	base_model	tags
apache-2.0	en ja	C C++ C# Go Java JavaScript Lua PHP Python Ruby Rust Scala TypeScript	text-generation	transformers	false	llm-jp/llm-jp-3-1.8b-instruct3	mlx

mlx-community/llm-jp-3-1.8b-instruct3

The Model mlx-community/llm-jp-3-1.8b-instruct3 was converted to MLX format from llm-jp/llm-jp-3-1.8b-instruct3 using mlx-lm version 0.21.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/llm-jp-3-1.8b-instruct3")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)