metadata
license: mit
library_name: mlx
datasets:
- PrimeIntellect/verifiable-coding-problems
- likaixin/TACO-verified
- livecodebench/code_generation_lite
language:
- en
base_model: gingofthesouth/DeepCoder-1.5B-MLX
pipeline_tag: text-generation
tags:
- mlx
- mlx
- mlx-my-repo
introvoyz041/DeepCoder-1.5B-MLX-mlx-4Bit
The Model introvoyz041/DeepCoder-1.5B-MLX-mlx-4Bit was converted to MLX format from gingofthesouth/DeepCoder-1.5B-MLX using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/DeepCoder-1.5B-MLX-mlx-4Bit")
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)