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
+Pythia-Chat-Base-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Pythia-Chat-Base-7B.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Pythia-Chat-Base-7B.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Pythia-Chat-Base-7B.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Pythia-Chat-Base-7B.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d1c48a1b980a5a12f39a5c1e24c57c7c643773769217ef420081f88bd14044
+size 13719821408

Pythia-Chat-Base-7B.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f128f265e8f04d4006dc0041b63428530809620a64e077122ba4c79991886e6
+size 5620620416

Pythia-Chat-Base-7B.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99c570d1dbb095afc610efd9286f5fa30272818aa1dfda3305089747d1cb44b
+size 6119742592

Pythia-Chat-Base-7B.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de85bb37e65ca7df34f9eafc3f827f685fb4da015b6ce2f379c606eec7fc0df
+size 7680023680

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.