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
commit c54bf95e92
8 changed files with 76 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,17 @@
+
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+---
+
+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