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
+Meta-Llama-3-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Meta-Llama-3-8B-Instruct.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2296999531d6120801529a45b1d103f7370c5970be939ebfc2ba5d0833e9e1e
+size 16068890912

Meta-Llama-3-8B-Instruct.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41764bc2e639fa8dd084b087ec66cf0f9d06d5999a7434ea1dd10f0fca71246
+size 7042224416

Meta-Llama-3-8B-Instruct.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e45f8e321498289c758ded6e443a1a4faeb2ac7595107b3d4102a54f1c988c
+size 7835472160

Meta-Llama-3-8B-Instruct.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ac180019ceefdee35c490698d1f479745722fb9d38ab6feb02a161377672ab
+size 9525776672

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: Wed Jul 10, 03:23:42