README.md

metadata

license: other
license_name: llm-jp-3-172b-instruct3-tou
license_link: https://huggingface.co/llm-jp/llm-jp-3-172b-instruct3/raw/main/LICENSE
language:
  - en
  - ja
programming_language:
  - C
  - C++
  - C#
  - Go
  - Java
  - JavaScript
  - Lua
  - PHP
  - Python
  - Ruby
  - Rust
  - Scala
  - TypeScript
pipeline_tag: text-generation
library_name: transformers
inference: false
tags:
  - mlx
base_model: llm-jp/llm-jp-3-172b-instruct3

schroneko/llm-jp-3-172b-instruct3-Q4-mlx

The Model schroneko/llm-jp-3-172b-instruct3-Q4-mlx was converted to MLX format from llm-jp/llm-jp-3-172b-instruct3 using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("schroneko/llm-jp-3-172b-instruct3-Q4-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)