commit 543bef71c7961d375e02c5597639ca2525bb851c Author: ModelHub XC Date: Thu Jun 18 15:39:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Infinite-Sumika-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b5bba84 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Infinite-Sumika-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinite-Sumika-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Infinite-Sumika-9B.IQ4_XS.gguf b/Infinite-Sumika-9B.IQ4_XS.gguf new file mode 100644 index 0000000..ae0f395 --- /dev/null +++ b/Infinite-Sumika-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633983bb0fc5d36cda41fa40d481ef4d5e5bf536baacc873bacf0ed63cdb0b18 +size 4886015232 diff --git a/Infinite-Sumika-9B.Q2_K.gguf b/Infinite-Sumika-9B.Q2_K.gguf new file mode 100644 index 0000000..0fcf94b --- /dev/null +++ b/Infinite-Sumika-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8017ef25345078c384a3b5b62aefba56a659d4f9eeb6d8b2572181451bdabc38 +size 3361238272 diff --git a/Infinite-Sumika-9B.Q3_K_L.gguf b/Infinite-Sumika-9B.Q3_K_L.gguf new file mode 100644 index 0000000..e465ad9 --- /dev/null +++ b/Infinite-Sumika-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acfa190e7a64eee4bc4407558da87f9d4e7c89932f66b687a62adf9507016088 +size 4736388352 diff --git a/Infinite-Sumika-9B.Q3_K_M.gguf b/Infinite-Sumika-9B.Q3_K_M.gguf new file mode 100644 index 0000000..122dc20 --- /dev/null +++ b/Infinite-Sumika-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847d586c3753f1f55c899eca0f9fb9d0fd17929613606ed6bb79dbad30992f6e +size 4353658112 diff --git a/Infinite-Sumika-9B.Q3_K_S.gguf b/Infinite-Sumika-9B.Q3_K_S.gguf new file mode 100644 index 0000000..21ad616 --- /dev/null +++ b/Infinite-Sumika-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19b764697d13142a3ee896e6df26cc96c8e3db5fcea137b147100e7f8e9ea22 +size 3914566912 diff --git a/Infinite-Sumika-9B.Q4_K_M.gguf b/Infinite-Sumika-9B.Q4_K_M.gguf new file mode 100644 index 0000000..713f216 --- /dev/null +++ b/Infinite-Sumika-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b45c45b420461ed60cb2e79f7827a1b59ba9c5f726900a46cdb55d7f483659 +size 5415054592 diff --git a/Infinite-Sumika-9B.Q4_K_S.gguf b/Infinite-Sumika-9B.Q4_K_S.gguf new file mode 100644 index 0000000..a571eeb --- /dev/null +++ b/Infinite-Sumika-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adbaafd2b30f71411ab049d6e1e83845af6c22e75a68b66cb8856205bdd90208 +size 5129448704 diff --git a/Infinite-Sumika-9B.Q5_K_M.gguf b/Infinite-Sumika-9B.Q5_K_M.gguf new file mode 100644 index 0000000..912e380 --- /dev/null +++ b/Infinite-Sumika-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3177612e08ebefabdfe9b11feb3b4db7173808aeaadb3a1fed4d83f2f49c3b5b +size 6364671232 diff --git a/Infinite-Sumika-9B.Q5_K_S.gguf b/Infinite-Sumika-9B.Q5_K_S.gguf new file mode 100644 index 0000000..3b30108 --- /dev/null +++ b/Infinite-Sumika-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65262ccc54d2fcf90454a23cb84424e56743142582258c26af9305916ce0c9a2 +size 6197554432 diff --git a/Infinite-Sumika-9B.Q6_K.gguf b/Infinite-Sumika-9B.Q6_K.gguf new file mode 100644 index 0000000..92f2e31 --- /dev/null +++ b/Infinite-Sumika-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ea3a787539a010b8d147b4fe1371b725e0e86105b68e7621248e9d41c28be1 +size 7373638912 diff --git a/Infinite-Sumika-9B.Q8_0.gguf b/Infinite-Sumika-9B.Q8_0.gguf new file mode 100644 index 0000000..74e8042 --- /dev/null +++ b/Infinite-Sumika-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b5acc9b2a8c8a5ec6153d841a06206629813af75433b301f02d6e1a3dc5bb8 +size 9550007552 diff --git a/Infinite-Sumika-9B.f16.gguf b/Infinite-Sumika-9B.f16.gguf new file mode 100644 index 0000000..c980c99 --- /dev/null +++ b/Infinite-Sumika-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dbf0d4ad083e4f4d3f5150924cf1cc721395edb651a3522852b68009dbb5234 +size 17974660352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..53ee875 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ABX-AI/Infinite-Sumika-9B +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- mergekit +- merge +- not-for-all-audiences +--- +## About + + + + + + +static quants of https://huggingface.co/ABX-AI/Infinite-Sumika-9B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Infinite-Sumika-9B-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.IQ4_XS.gguf) | IQ4_XS | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q5_K_S.gguf) | Q5_K_S | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q5_K_M.gguf) | Q5_K_M | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q6_K.gguf) | Q6_K | 7.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Infinite-Sumika-9B-GGUF/resolve/main/Infinite-Sumika-9B.f16.gguf) | f16 | 18.1 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +