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

license	library_name	datasets	language	base_model	pipeline_tag	tags
mit	mlx	PrimeIntellect/verifiable-coding-problems likaixin/TACO-verified livecodebench/code_generation_lite	en	agentica-org/DeepCoder-14B-Preview	text-generation	mlx

mlx-community/DeepCoder-14B-Preview-bf16

This model mlx-community/DeepCoder-14B-Preview-bf16 was converted to MLX format from agentica-org/DeepCoder-14B-Preview using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepCoder-14B-Preview-bf16")

prompt = "hello"

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

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