metadata

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

thr3a/llm-jp-3-1.8b-instruct-mlx

The Model thr3a/llm-jp-3-1.8b-instruct-mlx was converted to MLX format from mlx-community/llm-jp-3-1.8b-instruct using mlx-lm version 0.18.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("thr3a/llm-jp-3-1.8b-instruct-mlx")

prompt="hello"

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

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