Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Phi-3-mini-128k-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-mini-128k-instruct.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-mini-128k-instruct.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-mini-128k-instruct.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Phi-3-mini-128k-instruct.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b752a7f11dfbc8b7e6e50c2b19d2b3426f0414b908679e5fd461cd83a1d11c
+size 7643296608

Phi-3-mini-128k-instruct.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbde3e2b63187819365515e86f9671717aaee3607a2c8728e4f108b685631580
+size 3060757344

Phi-3-mini-128k-instruct.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe604f17bb8ec87903116495fdc058b12faf121f39b6f76060a043956bbf90b
+size 3368252256

Phi-3-mini-128k-instruct.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af03c4bfa10d673e37b145adc0e4eebea29a02bfdbe8a8d8142a7111a11e3faa
+size 4245910368

README.md

@@ -0,0 +1,14 @@
+
+---
+license: mit
+language:
+- en
+---
+
+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.