niryuu/llm-jp-3-13b-instruct-test-gguf

The Model niryuu/llm-jp-3-13b-instruct-test-gguf was converted to MLX format from llm-jp/llm-jp-3-13b using mlx-lm version 0.19.3.

Then, fine-tuned using llm-jp/databricks-dolly-15k-ja.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("niryuu/llm-jp-3-13b-instruct-test-gguf")

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)