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
+Lumimaid-v0.2-12B.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Lumimaid-v0.2-12B.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+Lumimaid-v0.2-12B.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Lumimaid-v0.2-12B.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Lumimaid-v0.2-12B.q8_p.gguf filter=lfs diff=lfs merge=lfs -text

Lumimaid-v0.2-12B.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05618189ac0614dbc5130dcbfe23beb800571d1f936b56c7021b890ad0bddd5d
+size 24504296576

Lumimaid-v0.2-12B.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51df1640b64840490ddc70699140f94d1b948d4a73e22bbc56da7394caf3424b
+size 10400130176

Lumimaid-v0.2-12B.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51828cedcb4cee48c859c432e309ab62571e6c9b66f9273bfd2af31206db5a57
+size 11639579776

Lumimaid-v0.2-12B.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632b0c190d7276e99cce265d47f1fcf487046135528ecbf7be67e883d22defe7
+size 14280680576

Lumimaid-v0.2-12B.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e58a86d8823b0585bf114d0f417dd2edbb95427b4d1f94919a36f64a539a2a
+size 13022379776

README.md

@@ -0,0 +1,17 @@
+
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+---
+
+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: Sat Jul 27, 12:28:10