taoki
/

deepseek-coder-7B-instruct-ja-stackoverflow-GGUF

Model card Files Files and versions Community

Edit model card

Deepseek Coder 7B Instruct ja-stackoverflow SFT - GGUF

Description

This repository contains a model trained (QLoRA-SFT) with the following data:

Base model: Deepseek Coder 7B Instruct v1.5
Training data: 日本語版 Stack Overflow
- accepted_answer_score > 2 and popular_answer_score > 2

Downloads last month: 52

GGUF

Model size

6.89B params

Architecture

llama

Unable to determine this model's library. Check the docs .

Quantized from

Dataset used to train taoki/deepseek-coder-7B-instruct-ja-stackoverflow-GGUF