metadata

license: apache-2.0
language:
  - en
  - ja
programming_language:
  - C
  - C++
  - C#
  - Go
  - Java
  - JavaScript
  - Lua
  - PHP
  - Python
  - Ruby
  - Rust
  - Scala
  - TypeScript
pipeline_tag: text-generation
library_name: mlx
inference: false
base_model: llm-jp/llm-jp-3.1-1.8b-instruct4
tags:
  - mlx

mlx-community/llm-jp-3.1-1.8b-instruct4-4bit

This model mlx-community/llm-jp-3.1-1.8b-instruct4-4bit was converted to MLX format from llm-jp/llm-jp-3.1-1.8b-instruct4 using mlx-lm version 0.24.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/llm-jp-3.1-1.8b-instruct4-4bit")

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)