Llama-3.1-Swallow-8B-Instruct-v0.2/README.md

language, library_name, pipeline_tag, license, model_type, datasets, base_model, tags

language	library_name	pipeline_tag	license	model_type	datasets	base_model	tags
en ja	transformers	text-generation	llama3.1 gemma	llama	lmsys/lmsys-chat-1m tokyotech-llm/lmsys-chat-1m-synth argilla/magpie-ultra-v0.1	tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2	mlx

mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.2

The Model mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.2 was converted to MLX format from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2 using mlx-lm version 0.19.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.2")

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)