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
+Mistral-Nemo-Base-2407.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Base-2407.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Base-2407.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Base-2407.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Base-2407.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

Mistral-Nemo-Base-2407.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01474d2e557ca7e7ee257fe9d0fc7bda4585be949a21b2dea786418fb3802e6
+size 24504275520

Mistral-Nemo-Base-2407.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6e7782321b42968b8483a6b10fb6597c75c6f5adde9fde5b8fc416d871f817
+size 10400109120

Mistral-Nemo-Base-2407.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84141530a4f878e479104539a47551845090ca02b9cf294ce74abba57abaa47
+size 11639558720

Mistral-Nemo-Base-2407.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdaeac994e57933160ba50b5cae73efeeb400146375070b8a4412ad96af9b6b8
+size 14280659520

Mistral-Nemo-Base-2407.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7948e48468f6653d24fd2bad482ef432a49c07b368f1146171de83e7515fd1
+size 13022368320

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: Mon Jul 22, 19:11:01