Strand-Rust-Coder-14B-v1-mlx-fp16/README.md

license, datasets, base_model, pipeline_tag, library_name, tags

license	datasets	base_model	pipeline_tag	library_name	tags
apache-2.0	Fortytwo-Network/Strandset-Rust-v1	Fortytwo-Network/Strand-Rust-Coder-14B-v1	text-generation	transformers	mlx

afimin/Strand-Rust-Coder-14B-v1-mlx-fp16

The Model afimin/Strand-Rust-Coder-14B-v1-mlx-fp16 was converted to MLX format from Fortytwo-Network/Strand-Rust-Coder-14B-v1 using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("afimin/Strand-Rust-Coder-14B-v1-mlx-fp16")

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)