This model is a merged version of two Qwen base models: — Qwen/Qwen3-4B-Instruct-2507 — Qwen/Qwen3-4B-Thinking-2507 — 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. — For my evaluation in my agent benchmark is not surpass too much but only 3% with instruct model. — Превзойти openfree/Darwin-Qwen3-4B (модель эволюции) и базовую модель в ACEBench. bibtex @misc{nafyqwenmerge2025, 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} }
Модальности:
Генерация текста
Области применения:
Математика Диалог / чат
Задача: Генерация текста
Автор: beyoru
Теги: qwen3, evoluation, math, merge, conversational, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 118
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
