File size: 295 Bytes
f91f970 808c956 |
1 2 3 4 5 6 7 |
---
license: apache-2.0
---
Posting these Qwen-14B-Chat quantized models in GGUF format for use with `llama.cpp` due to a user request.
But, having used an importance matrix derived from English-only training data in the quantization, I have no idea how these models will perform in Chinese. |