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
+llama-3-Nephilim-v3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-Nephilim-v3-8B.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-Nephilim-v3-8B.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-Nephilim-v3-8B.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-Nephilim-v3-8B.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: Mon Jul 22, 11:15:39

llama-3-Nephilim-v3-8B.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f34d92bf9e9b530d6b40dbad165d896cd0ecf329d63ffdb85872a25541b5db
+size 16068891936

llama-3-Nephilim-v3-8B.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0de3256e9842a95ecd21c84d549299dd659134791a5d6c1464bd5b1c260242
+size 7042225440

llama-3-Nephilim-v3-8B.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f52a5afd39e6a4589c7e8cd843b0eb0d5706c26fc4328e71b3451d8b4abac1
+size 7835473184

llama-3-Nephilim-v3-8B.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddad623101ed1b2798c92eac2e1bea5051e1e2949d201c37520e971d656511d7
+size 9525777696

llama-3-Nephilim-v3-8B.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df67086c132201d4f5e47dc5c12c90d9c9e0513663323e41031b37031d6386f
+size 8540771616