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-7b-fc-r.f16.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-7b-fc-r.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-7b-fc-r.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-7b-fc-r.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+xLAM-7b-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, 21:48:48

xLAM-7b-fc-r.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e9889042c465f76a1bf7cd0e56373bf0d07566a158e631a5d358ab056a57d7
+size 13825218688

xLAM-7b-fc-r.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8caea19e923cd7f2b8495c066213d3a37860bf9a44f1f14c3022b7bc9a06f0e1
+size 5971728512

xLAM-7b-fc-r.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fafe50d1545a77a0fc08e4b0a972245a1d53ba1e06a1b15c1c12f0a5388d1ef
+size 6663035008

xLAM-7b-fc-r.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2105c3ce958ba8110d5463384bc1558084462ca9992360c1bb9449910e260fb
+size 8133417088

xLAM-7b-fc-r.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa19728cd20177a5a0fb7e81a334061968da295da3d1af69a8f3f0ee2919e5b
+size 7346985088