Qwen2.5-Coder-1.5B-GGUF Open Source Code Model - Supports Multilingual Code Completion and Generation

Qwen2.5 Coder 1.5B GGUF

Developed by tensorblock

Qwen2.5-Coder-1.5B is a code generation model with 1.5B parameters, supporting multiple programming languages and suitable for code completion and generation tasks.

Large Language Model

Transformers

Supports Multiple LanguagesOpen Source License:Apache-2.0 #Code generation #Lightweight model #Multiple quantization versions

Downloads 162

Release Time : 11/10/2024

Model Overview

Qwen2.5-Coder-1.5B is a code generation model based on the Transformer architecture, designed specifically for code completion and generation tasks and supporting multiple programming languages.

Model Features

Multiple quantization options

Provide multiple quantization options from Q2_K to Q8_0 to meet the performance and accuracy requirements in different scenarios.

Efficient inference

Optimized through the GGUF format, supporting efficient inference on devices with limited resources.

Strong code generation ability

Optimized specifically for code generation and completion tasks, supporting multiple programming languages.

Model Capabilities

Code generation

Code completion

Programming language understanding

Use Cases

Software development

Code completion

Complete code in real-time in the IDE to improve development efficiency.

Significantly reduce coding time and improve code quality.

Code generation

Generate code snippets based on natural language descriptions.

Quickly generate runnable code and reduce the workload of manual coding.

🚀 Qwen/Qwen2.5-Coder-1.5B - GGUF

This repository stores GGUF format model files for Qwen/Qwen2.5-Coder-1.5B, offering efficient and accessible model usage.

🚀 Quick Start

This repo contains GGUF format model files for Qwen/Qwen2.5-Coder-1.5B. The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

✨ Features

Our projects

Project	Details
Awesome MCP Servers	A comprehensive collection of Model Context Protocol (MCP) servers. 👉 See what we built 👉
TensorBlock Studio	A lightweight, open, and extensible multi-LLM interaction studio. 👉 See what we built 👉

Project	Image
Awesome MCP Servers
TensorBlock Studio

📚 Documentation

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
Qwen2.5-Coder-1.5B-Q2_K.gguf	Q2_K	0.630 GB	smallest, significant quality loss - not recommended for most purposes
Qwen2.5-Coder-1.5B-Q3_K_S.gguf	Q3_K_S	0.709 GB	very small, high quality loss
Qwen2.5-Coder-1.5B-Q3_K_M.gguf	Q3_K_M	0.768 GB	very small, high quality loss
Qwen2.5-Coder-1.5B-Q3_K_L.gguf	Q3_K_L	0.820 GB	small, substantial quality loss
Qwen2.5-Coder-1.5B-Q4_0.gguf	Q4_0	0.871 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Qwen2.5-Coder-1.5B-Q4_K_S.gguf	Q4_K_S	0.876 GB	small, greater quality loss
Qwen2.5-Coder-1.5B-Q4_K_M.gguf	Q4_K_M	0.918 GB	medium, balanced quality - recommended
Qwen2.5-Coder-1.5B-Q5_0.gguf	Q5_0	1.023 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Qwen2.5-Coder-1.5B-Q5_K_S.gguf	Q5_K_S	1.023 GB	large, low quality loss - recommended
Qwen2.5-Coder-1.5B-Q5_K_M.gguf	Q5_K_M	1.048 GB	large, very low quality loss - recommended
Qwen2.5-Coder-1.5B-Q6_K.gguf	Q6_K	1.185 GB	very large, extremely low quality loss
Qwen2.5-Coder-1.5B-Q8_0.gguf	Q8_0	1.533 GB	very large, extremely low quality loss - not recommended

📦 Installation

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, download the individual model file to a local directory

huggingface-cli download tensorblock/Qwen2.5-Coder-1.5B-GGUF --include "Qwen2.5-Coder-1.5B-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Qwen2.5-Coder-1.5B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

📄 License

This project is licensed under the Apache-2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご