abdulloh19291/super-model-7b

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Apr 21, 2026Architecture:Transformer Cold

abdulloh19291/super-model-7b is a 7.6 billion parameter language model created by merging Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct, and DeepSeek-R1-Distill-Qwen-7B using the DARE TIES method. This model leverages the strengths of its base components, including a strong coding foundation, to offer enhanced general instruction following and specialized capabilities. With a 32K context length, it is suitable for tasks requiring both broad understanding and code-related reasoning.

Loading preview...

Model Overview

abdulloh19291/super-model-7b is a 7.6 billion parameter language model developed through a merge of several pre-trained models using the DARE TIES method. The base model for this merge was Qwen/Qwen2.5-7B-Instruct, which provides a robust foundation for instruction following. The merge also incorporated Qwen/Qwen2.5-Coder-7B-Instruct and deepseek-ai/DeepSeek-R1-Distill-Qwen-7B.

Key Capabilities

  • Enhanced Instruction Following: Benefits from the strong instruction-tuned base of Qwen2.5-7B-Instruct.
  • Code Generation and Understanding: Integrates capabilities from Qwen2.5-Coder-7B-Instruct and DeepSeek-R1-Distill-Qwen-7B, making it proficient in coding tasks.
  • Merged Strengths: Combines the distinct advantages of its constituent models to offer a more versatile and capable LLM.
  • Extended Context: Supports a context length of 32,768 tokens, suitable for processing longer inputs and maintaining conversational coherence.

Good For

  • General-purpose AI applications requiring reliable instruction adherence.
  • Software development tasks, including code generation, debugging, and explanation.
  • Complex problem-solving that benefits from a blend of general knowledge and specialized coding expertise.