# Programming assistance

An open-source code reasoning large language model developed by NVIDIA, with a parameter scale of 14 billion, focused on code generation and reasoning tasks.

An open-source generative text model fine-tuned based on Deepseek-coder-1.3B, focusing on Kotlin code generation tasks

StarCoder2-3B is a code generation model with 3 billion parameters. It is trained on data from 17 programming languages and can generate code snippets, but the results may not be completely accurate.

The first open-source large language model trained with AI Feedback Reinforcement Learning (RLAIF), demonstrating excellent performance in MT Bench tests

CodeFuse-13B is a 13-billion-parameter code generation model trained on the GPT-NeoX framework, supporting over 40 programming languages and capable of processing code sequences up to 4096 characters long.

StarCoderBase-7B is a code generation model with 7 billion parameters, supporting over 80 programming languages and focusing on code completion and generation tasks.

This is a Python code generation model with 164 million parameters, based on the StarCoder architecture, specifically optimized for Python code generation tasks.

A Python code generation model fine-tuned based on Salesforce/codet5-small, specializing in custom function generation tasks

A Python code generation model fine-tuned based on Salesforce/codegen-350M-mono, focusing on custom function generation

CodeParrot is a Python code generation model based on the GPT-2 architecture (1.5 billion parameters), focusing on automatic Python code generation.