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
+Qwen1.5-7B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen1.5-7B-Chat.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen1.5-7B-Chat.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen1.5-7B-Chat.q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Qwen1.5-7B-Chat.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2bf036ced4809400cac0272f7e21cb822bb46432f23764385b8e88761a5cbb
+size 15449918816

Qwen1.5-7B-Chat.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ef7c09d7aa7008e9b2f0b5b1438d2c3b68c250a2a7aa2d659c5230ad8eec9a
+size 7081626976

Qwen1.5-7B-Chat.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b9b1a7bc6be4de744a4c4dcc1b7b193eb9ccacdf07ebfd599e8333f24bea70
+size 7810256224

Qwen1.5-7B-Chat.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217fd1bfe780126c8b99e8a3e8c239c6355a8bfeadf20cfb4b177763be962a16
+size 9378663776

README.md

@@ -0,0 +1,14 @@
+
+---
+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.