commit 335baba79bcf6f6041d29cdc62bbe26f99accb2a Author: ModelHub XC Date: Sun May 10 14:40:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ZeroWw/Gemmasutra-Mini-2B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f834cde --- /dev/null +++ b/.gitattributes @@ -0,0 +1,41 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +Gemmasutra-Mini-2B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.q5_k.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.q8_p.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.q8q4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemmasutra-Mini-2B-v1.f16.gguf b/Gemmasutra-Mini-2B-v1.f16.gguf new file mode 100644 index 0000000..f5b219a --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52fbdd0091ca1437146e47265c2404c86b0d242213061fa13c33fc74eacd3a39 +size 5235213856 diff --git a/Gemmasutra-Mini-2B-v1.q5_k.gguf b/Gemmasutra-Mini-2B-v1.q5_k.gguf new file mode 100644 index 0000000..65a9a44 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.q5_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f657298e3d95b1603522ae85614a15ebda3fffea6093191f04d3e151532586 +size 2619086368 diff --git a/Gemmasutra-Mini-2B-v1.q6_k.gguf b/Gemmasutra-Mini-2B-v1.q6_k.gguf new file mode 100644 index 0000000..786b227 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5a155a483ef12168c88561d5422d364fecb609dd37c580adcd308a545ed318 +size 2847200800 diff --git a/Gemmasutra-Mini-2B-v1.q8_0.gguf b/Gemmasutra-Mini-2B-v1.q8_0.gguf new file mode 100644 index 0000000..2035277 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d7371c8dce03f9017a1b5f317a501ca84710b1e69440398ebdcfee04e10217 +size 3337455136 diff --git a/Gemmasutra-Mini-2B-v1.q8_p.gguf b/Gemmasutra-Mini-2B-v1.q8_p.gguf new file mode 100644 index 0000000..59c3915 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.q8_p.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4748008f3e7185fa4bf90ccf919bec470185d9ed3335ea356614a68e8d2024f1 +size 2784495136 diff --git a/Gemmasutra-Mini-2B-v1.q8q4.gguf b/Gemmasutra-Mini-2B-v1.q8q4.gguf new file mode 100644 index 0000000..8ae323e --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.q8q4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe28f96b296ca39d297a7c1d7c18b13090819a527d0b13013b87b5e4a1a83fee +size 1851430432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..59a4523 --- /dev/null +++ b/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 Aug 03, 17:55:22