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-7B-Instruct-v0.3.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

Mistral-7B-Instruct-v0.3.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72a0b2e3ad353195e88875705ad2d5f2d56cd2a54e77479519b8f3ee949ea8a
+size 14497338176

Mistral-7B-Instruct-v0.3.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51de8e5e4abe5a0ce6f62d81729d9e6e956d80adf1bb5a22c75fc80b981f3529
+size 5470671680

Mistral-7B-Instruct-v0.3.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30eea4b854f35095cc0f44017c315a46725629bcd86e4b45e2b7899463554d10
+size 6263919424

Mistral-7B-Instruct-v0.3.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d441f655d8cd1878131d6dc19327fff40d0e08b54c4d1864eb2cd8373257403
+size 7954223936

Mistral-7B-Instruct-v0.3.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ff3a6176474304ccaba670ab2404517f5147b426d56134a79ec3a25fd90241
+size 7702565696

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 19, 18:50:44