README.md

metadata

base_model: unsloth/qwen2.5-coder-7b-instruct-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen2
license: apache-2.0
language:
  - en

Qwen2.5-CoderX-7B-v0.7

With the correct prompting and settings: temperature = 1.5, min_p = 0.1, the model should produce outputs that are close or on-par with proprietary models like Gemini 2.5 Pro.

This model provides deep, production-ready responses. For shorter outputs, try prompts like 'be concise' or 'code only'."