Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+xLAM-1b-fc-r.f16.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-1b-fc-r.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-1b-fc-r.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-1b-fc-r.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-1b-fc-r.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,16 @@
+
+---
+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.
+
+Updated on: Fri Jul 19, 21:25:25

xLAM-1b-fc-r.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc45a69ec20335f7e83b9a3188a56f5b209f7c967a411e30beaeacb11ad4aeb0
+size 2694314848

xLAM-1b-fc-r.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e0d3ae360bbfac3a4d293f9bedd1049bb2091eaca942327a1b30c4fb724c0a6
+size 1166474080

xLAM-1b-fc-r.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979451a859ab0fce55b45e402901c76aa247a0ef3673cd966c8c2e2f8c648044
+size 1327397728

xLAM-1b-fc-r.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37347528996dc95ef5e69c182ee399adf3f72f78cba64c42c837294f97834a87
+size 1555954528

xLAM-1b-fc-r.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e3f4ccb3968a326edb0c6874dd0d6404c19db8dbeecd62e8dee50be1c917c0
+size 1432091488