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
+DeepSeek-V2-Lite-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-V2-Lite-Chat.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-V2-Lite-Chat.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-V2-Lite-Chat.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

DeepSeek-V2-Lite-Chat.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef9ac89c78b82e188cad8c75d0cb630899e08510a97d6fa41431139573f697c
+size 31424033088

DeepSeek-V2-Lite-Chat.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf6bf59712b5547e74e8fd090ea5a940d251878bbb0ff5aa862c244290d96dd
+size 12373963072

DeepSeek-V2-Lite-Chat.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2afc0ea9f1c7fd2f9314ec7976e4d5436174dea13da3abe28e6197ad59c5edd
+size 14561768768

DeepSeek-V2-Lite-Chat.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffc5ecebac0eef5574f73c50ac64cb672eca07e4679bd3c6a2e85f4ded1d249
+size 17095733568

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 12, 12:43:21