Phi-3.5-mini-instruct_Uncensored-GGUF

Go to file

ModelHub XC c54bf95e92 初始化项目，由ModelHub XC社区提供模型

Model: ZeroWw/Phi-3.5-mini-instruct_Uncensored-GGUF
Source: Original Platform

2026-04-20 19:05:23 +08:00

.gitattributes

2026-04-20 19:05:23 +08:00

2026-04-20 19:05:23 +08:00

2026-04-20 19:05:23 +08:00

2026-04-20 19:05:23 +08:00

2026-04-20 19:05:23 +08:00

2026-04-20 19:05:23 +08:00

2026-04-20 19:05:23 +08:00

README.md

2026-04-20 19:05:23 +08:00

license: mit language:

My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5_k or q6_k.

Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.

Updated on: Thu Aug 22, 13:56:30