DeepSeek Coder CLI

A lightweight terminal-based chat interface for DeepSeek-Coder-6.7B-Instruct using llama.cpp. Supports streaming responses, multi-turn conversations, file attachments, and CPU performance benchmarking.

Requirements

• Python 3.10+
• llama.cpp (built with llama-server and llama-bench)
• DeepSeek-Coder-6.7B-Instruct GGUF model

No additional Python packages required.

Usage

Start an interactive chat:

python3 deepseek_chat.py

Send a one-shot prompt:

python3 deepseek_chat.py -p "Explain binary search trees"

Pipe a file into the model:

cat app.py | python3 deepseek_chat.py -p "Review this code"

Run a performance benchmark:

python3 deepseek_chat.py --bench

Keep the server running:

python3 deepseek_chat.py --serve-only

What I did was to make it less wordy (.zshrc or bashrc):

alias ds-chat='python3 deepseek_chat.py'

Interactive Commands

Command	Description
/file PATH	Attach a file to the next message
/system [TXT]	View or change the system prompt
/temp X	Change temperature
/max N	Set maximum response tokens
/reset	Clear conversation history
/save PATH	Save conversation as Markdown
/help	Display available commands
/exit	Exit the application

Configuration

Command-line options allow customization of context size, CPU threads, KV cache precision, sampling parameters, and server arguments. Run:

python3 deepseek_chat.py --help

The code has been commented using Doxygen blocks for better readability/usability.