ocm-coder

LoRA adapters fine-tuned on the Open Component Model (OCM) and OCI specification ecosystem.

Base model: mlx-community/Qwen2.5-Coder-32B-Instruct-4bit

Usage

from mlx_lm import load, generate

model, tokenizer = load(
    "mlx-community/Qwen2.5-Coder-32B-Instruct-4bit",
    adapter_path="piotrjanik/ocm-coder",
)
Downloads last month
23
MLX
Hardware compatibility
Log In to add your hardware

Quantized

GGUF
Model size
33B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for piotrjanik/ocm-coder