awq version of agentica-org/DeepCoder-14B-Preview

quant_config = {
    "zero_point": True,
    "q_group_size": 128,
    "w_bit": 4,
    "version": "GEMM"
}

Safetensors

Model size

3.33B params

Tensor type

F32

I32

FP16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support