# Programming assistant

A large language model fine-tuned specifically for Rust code middle infilling (FIM) tasks, built upon JetBrains/Mellum-4b-base

A code reasoning model fine-tuned based on Qwen2.5-Coder-1.5B-Instruct, which enhances programming problem-solving and logical reasoning abilities

IBM Granite 8B code instruction model, supporting a context length of 128k, focusing on code generation and instruction understanding tasks.

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.

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.

Codestral-22B-v0.1 is a large-scale code generation model developed by Mistral AI, supporting over 80 programming languages, suitable for code generation, explanation, and refactoring tasks.

CodeLlama 70B Python is a large language model focused on the Python programming language, based on the Llama 2 architecture, optimized for code generation and completion tasks.

TinyLlama is a lightweight 1.1B-parameter Llama model optimized for chat and programming assistance tasks.

Magicoder is a new model family empowered by OSS-Instruct, generating low-bias and high-quality code instruction data inspired by open-source code snippets, specifically designed for coding tasks.

Magicoder is a family of code generation models powered by OSS-Instruct technology, leveraging open-source code snippets to inspire LLMs to generate high-quality code instruction data

WizardCoder Python 13B V1.0 is a large language model developed by WizardLM, focusing on Python code generation tasks. It is based on the llama2 architecture and performs excellently in the HumanEval benchmark test.

StarCoder is a 15.5B-parameter code generation model trained on over 80 programming languages, supporting a context window of 8192 tokens