A Jev-style model fine-tuned on Qwen3.5 4B
英文标题：A Jev-style model fine-tuned on Qwen3.5 4B
This weekend, I did a fun experiment to create something similar to Jev. I LoRA fine-tuned Qwen3.5 4B using a mix of publicly available datasets and synthetic data. For the synthetic data, I used DeepSeek V4.1 Flash, around 25M tokens. I trained the model for about 2 hours on a rented RTX 3090. So f
打开原文相关 2 · 机会 0
中文
This weekend, I did a fun experiment to create something similar to Jev. I LoRA fine-tuned Qwen3.5 4B using a mix of publicly available datasets and synthetic data. For the synthetic data, I used DeepSeek V4.1 Flash, around 25M tokens. I trained the model for about 2 hours on a rented RTX 3090. So f
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
This weekend, I did a fun experiment to create something similar to Jev. I LoRA fine-tuned Qwen3.5 4B using a mix of publicly available datasets and synthetic data. For the synthetic data, I used DeepSeek V4.1 Flash, around 25M tokens. I trained the model for about 2 hours on a rented RTX 3090. So f