1. Introduction

This model is quantized version of DeepCoder-14B-Preview with dataset for imatrix TFMC/imatrix-dataset-for-japanese-llm. Usgin English/Japanese mixed and quantization is tuned for Japanese.

2. License

This code repository and the model weights are licensed under the MIT License. Here is note for upstream model license:

  • DeepCoder-2.5B-Preview is based on DeepSeek-R1-Distill-Qwen-1.5B which has same MIT license as DeepCoder. But DeepSeek-R1-Distill-Qwen-1.5B are derived from Qwen-2.5 series, which are originally licensed under Apache 2.0 License,
Downloads last month
18
GGUF
Model size
1.78B params
Architecture
qwen2
Hardware compatibility
Log In to view the estimation

4-bit

8-bit

16-bit

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

Model tree for okamototk/DeepCoder-1.5B-Preview-imatrix-GGUF

Dataset used to train okamototk/DeepCoder-1.5B-Preview-imatrix-GGUF