ChatTime-1-7B-Base Open-Source Model - Free Deployment for Multimodal Time Series Prediction

Chengsenwang ChatTime 1 7B Base GGUF

Developed by tensorblock

ChatTime-1-7B-Base is a foundational model specialized in time series forecasting, supporting multimodal time series processing.

Multimodal Fusion Open Source License:Apache-2.0 #Time Series Forecasting #Multimodal Foundation Model #TensorBlock Optimization

Downloads 175

Release Time : 4/29/2025

Model Overview

This is a 7B-parameter foundational model for time series, suitable for forecasting and analysis tasks involving multimodal time series.

Model Features

Multimodal Time Series Processing

Supports processing various types of time series data

Efficient Quantization

Provides multiple quantized versions to accommodate different hardware requirements

Compatible with llama.cpp

Model files are compatible with the llama.cpp framework

Model Capabilities

Time Series Forecasting

Multimodal Data Processing

Long-term Trend Analysis

Use Cases

Financial Forecasting

Stock Price Prediction

Predict future stock price trends

Industrial Monitoring

Equipment Failure Prediction

Predict potential failures in industrial equipment

🚀 ChengsenWang/ChatTime-1-7B-Base - GGUF

This repository offers GGUF format model files for time - series forecasting, leveraging the base model ChengsenWang/ChatTime-1-7B-Base.

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

🚀 Quick Start

This repo contains GGUF format model files for ChengsenWang/ChatTime-1-7B-Base. The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.

✨ Features

Our projects

Project	Description	Link
Awesome MCP Servers	A comprehensive collection of Model Context Protocol (MCP) servers.	GitHub
TensorBlock Studio	A lightweight, open, and extensible multi - LLM interaction studio.	GitHub

📚 Documentation

Prompt template

Model file specification

Filename	Quant type	File Size	Description
ChatTime-1-7B-Base-Q2_K.gguf	Q2_K	2.580 GB	smallest, significant quality loss - not recommended for most purposes
ChatTime-1-7B-Base-Q3_K_S.gguf	Q3_K_S	3.000 GB	very small, high quality loss
ChatTime-1-7B-Base-Q3_K_M.gguf	Q3_K_M	3.349 GB	very small, high quality loss
ChatTime-1-7B-Base-Q3_K_L.gguf	Q3_K_L	3.649 GB	small, substantial quality loss
ChatTime-1-7B-Base-Q4_0.gguf	Q4_0	3.883 GB	legacy; small, very high quality loss - prefer using Q3_K_M
ChatTime-1-7B-Base-Q4_K_S.gguf	Q4_K_S	3.914 GB	small, greater quality loss
ChatTime-1-7B-Base-Q4_K_M.gguf	Q4_K_M	4.138 GB	medium, balanced quality - recommended
ChatTime-1-7B-Base-Q5_0.gguf	Q5_0	4.714 GB	legacy; medium, balanced quality - prefer using Q4_K_M
ChatTime-1-7B-Base-Q5_K_S.gguf	Q5_K_S	4.714 GB	large, low quality loss - recommended
ChatTime-1-7B-Base-Q5_K_M.gguf	Q5_K_M	4.845 GB	large, very low quality loss - recommended
ChatTime-1-7B-Base-Q6_K.gguf	Q6_K	5.597 GB	very large, extremely low quality loss
ChatTime-1-7B-Base-Q8_0.gguf	Q8_0	7.248 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Basic Usage

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, download the individual model file to a local directory

huggingface-cli download tensorblock/ChengsenWang_ChatTime-1-7B-Base-GGUF --include "ChatTime-1-7B-Base-Q2_K.gguf" --local-dir MY_LOCAL_DIR

Advanced Usage

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

huggingface-cli download tensorblock/ChengsenWang_ChatTime-1-7B-Base-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.

Dataset

ChengsenWang/ChatTime-1-Pretrain-1M

Pipeline tag

time-series-forecasting

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