# Programming Assistance

OpenR1-Distill-7B is a post-trained version of Qwen2.5-Math-7B on the Mixture-of-Thoughts dataset, designed to teach language models step-by-step reasoning.

Qwen2.5-Coder-7B-Instruct is a 7B-parameter code generation model based on the Qwen2.5 architecture, specializing in instruction fine-tuning, suitable for code generation and programming assistance tasks.

A 14B-parameter code generation and comprehension model based on the Qwen2.5 architecture, integrated through the Model Stock method by combining multiple specialized coding models

DeepCoder-14B-Preview is a code generation model developed based on DeepSeek-R1-Distill-Qwen-14B, focusing on solving verifiable programming problems.

A hybrid model based on Qwen2.5-Coder-14B-Instruct, merged using the mergekit tool with multiple specialized coding models

DeepSeek-V3-0324-Pruned-Coder-411B is a pruned and optimized code generation model based on the DeepSeek-V3 architecture, focusing on code generation tasks.

Qwen2.5-Coder-32B-instruct is an instruction fine-tuned version based on Qwen2.5-Coder-32B, specializing in code generation and understanding tasks.

The EXAONE Deep series models excel in reasoning tasks such as mathematics and programming. This model is the 4-bit AWQ quantized version with 2.4 billion parameters

This is a GGUF format model converted from the Qwen2.5-Coder-0.5B model, suitable for code generation tasks.

Code Llama is a series of 7 billion parameter code generation models developed by Meta, with this version specifically optimized for Python

This is a fine-tuned model based on TinyLlama-1.1B-Chat-v1.0, specifically designed to convert natural language questions and table structure definitions (DDL) into SQL queries.

The WhiteRabbitNeo series of models focuses on cybersecurity offense and defense applications, with the current version being a 7B parameter model capable of code generation and analysis.

OpenChat is an innovative open-source language model library that employs C-RLFT strategy for fine-tuning, achieving performance comparable to ChatGPT with just 7 billion parameters.

WizardCoder is a large language model for code enhanced by the Evol-Instruct method, specializing in code generation tasks.

CodeLlama 34B Instruct is a large-scale code generation model developed by Meta based on the Llama 2 architecture, specifically optimized for programming tasks and supporting multiple programming languages.

CodeLlama 13B is a code generation and comprehension model released by Meta, based on the Llama 2 architecture and specifically optimized for programming tasks.

CodeLlama 7B is a 7B-parameter code generation and comprehension model developed by Meta, optimized based on the Llama 2 architecture and focused on programming tasks.

Code Llama 13B is a 13-billion-parameter generative code model designed for general-purpose code synthesis and understanding

WizardCoder-33B-V1.1 is an open-source large language model for code, trained on deepseek-coder-33b-base, demonstrating excellent performance on code generation benchmarks like HumanEval.

A 125M-parameter code generation model based on the GPT-Neo architecture, fine-tuned on the CodeClippy dataset, supporting sequence generation up to 2048 tokens