EvolLLM / README.md
beyoru's picture
Update README.md
2fed81a verified
metadata
base_model:
  - Qwen/Qwen3-4B-Instruct-2507
  - Qwen/Qwen3-4B-Thinking-2507
library_name: transformers
datasets:
  - openai/gsm8k
tags:
  - evoluation
  - math
  - merge

📑 Model Card

💻Github Repo🤗Model Collections

Model Details

This model is a merged version of two Qwen base models:

  • Qwen/Qwen3-4B-Instruct-2507
  • Qwen/Qwen3-4B-Thinking-2507

Notations:

  • Evoluation dataset: openai/gsm8k (subset of 100 samples, not trained)
  • Generation runs: 50
  • Population size: 10
  • This model design for instruct model not reasoning model with same function like Qwen3-Instruct-2507
  • A good start for SFT or GRPO training.

Evaluation

  • For my evaluation in my agent benchmark is not surpass too much but only 3% with instruct model.
  • Surpass openfree/Darwin-Qwen3-4B (Evolution model) and base model in ACEBench.
@misc{nafy_qwen_merge_2025,
  title        = {Merged Qwen3 4B Instruct + Thinking Models},
  author       = {Beyoru},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/beyoru/EvolLLM}},
  note         = {Merged model combining instruction-tuned and reasoning Qwen3 variants.},
  base_models  = {Qwen/Qwen3-4B-Instruct-2507, Qwen/Qwen3-4B-Thinking-2507}
}