Models

CodeQwen1.5-7B-Chat 官方优化版本

使用 ms-swift 框架微调 Qwen1.5-7B-chat 模型并转换为 Ollama 支持格式的实践

We have trained a Xiaoyi dialogue robot model for the driving training field based on the Qwen1.5-7b model, using the method of QLora fine-tuning.

unsloth/Qwen2.5-7B-Instruct-1M

Qwen2.5-7B/14B-Instruct-1M

https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K-GGUF