Upload folder using huggingface_hub

Files changed (7) hide show

.gitattributes CHANGED Viewed

@@ -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

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Tiger-Gemma-9B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Tiger-Gemma-9B-v1.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Tiger-Gemma-9B-v1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Tiger-Gemma-9B-v1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Tiger-Gemma-9B-v1.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

+---
+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: Sun Jul 14, 06:57:46

Tiger-Gemma-9B-v1.f16.gguf ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:282eedf83a9cd8a165add4dd5bb83237704e8b97c40f58eaf71ff11d77dd6e41
+size 18490679968

Tiger-Gemma-9B-v1.q5_k.gguf ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:98233416595b939ce611bbaaada75aaab798e868c9f40f9bc508d7be889d1f78
+size 7729734304

Tiger-Gemma-9B-v1.q6_k.gguf ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:b35fd1eaec2f5dc6d53eb895313a6420a12d146e2a4977c24a792f64143db97e
+size 8671437472

Tiger-Gemma-9B-v1.q8_0.gguf ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:b633c74ffc7fa1e4943356b01786ad0171fe8205ec3957143b8dfe2bf1b54d6e
+size 10687308448

Tiger-Gemma-9B-v1.q8_p.gguf ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:fd67ef923455d634ab8a53ae86c300ff585aa709217bbc9284098c0fa331cb53
+size 9827148448