# Multi-programming language support

Seed-Coder is an 8B-scale open-source code model family, including base, instruction, and reasoning versions. The reasoning version enhances reasoning capabilities through reinforcement learning training and supports 64K context length.

A 1-billion parameter code encoder pre-trained on The Stack v2 dataset, featuring modular design and bidirectional self-attention mechanism

Granite-3B-Code-Instruct-128K is a long-context instruction model with 3 billion parameters, fine-tuned from Granite-3B-Code-Base-128K, specializing in coding-related tasks.

Code Llama is Meta's 34 billion parameter instruction-tuned code generation model, specifically designed for general code synthesis and understanding

Code Llama is a series of large language models for code generation and understanding developed by Meta, with the 34B version being the 34-billion-parameter base model

A Java code documentation generation model based on the T5 large architecture, supporting multi-task training and excelling in generating Java function descriptions