commit f29205480e041747e157e579a89af6225c6ff925 Author: ModelHub XC Date: Sun Oct 18 06:30:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Sumi-v0.5-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3ab30b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sumi-v0.5.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..43d2f84 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Oisu/Sumi-v0.5 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Oisu/Sumi-v0.5 + + +static quants are available at https://huggingface.co/mradermacher/Sumi-v0.5-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/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sumi-v0.5-i1-GGUF/resolve/main/Sumi-v0.5.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/Sumi-v0.5.i1-IQ1_M.gguf b/Sumi-v0.5.i1-IQ1_M.gguf new file mode 100644 index 0000000..37a546a --- /dev/null +++ b/Sumi-v0.5.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba909cc350e428e0fd5b375f08d7200c3c5b2426a420e0a03c3479b407c6d8f1 +size 1757663776 diff --git a/Sumi-v0.5.i1-IQ1_S.gguf b/Sumi-v0.5.i1-IQ1_S.gguf new file mode 100644 index 0000000..a8f2ef9 --- /dev/null +++ b/Sumi-v0.5.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2453efb0052a963f33845101cc289c6dd93b4623cb69388d245e601253db46e7 +size 1615319584 diff --git a/Sumi-v0.5.i1-IQ2_M.gguf b/Sumi-v0.5.i1-IQ2_M.gguf new file mode 100644 index 0000000..7ebe928 --- /dev/null +++ b/Sumi-v0.5.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8778d06e454de9a3a14c159d2945927d5ef7846d94c8f2e567ee68c70b97205b +size 2504249888 diff --git a/Sumi-v0.5.i1-IQ2_S.gguf b/Sumi-v0.5.i1-IQ2_S.gguf new file mode 100644 index 0000000..5225db3 --- /dev/null +++ b/Sumi-v0.5.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ad0556ea909256311f1d20072ef827ccf764ff749970583492900bd1b7c4f4 +size 2314457632 diff --git a/Sumi-v0.5.i1-IQ2_XS.gguf b/Sumi-v0.5.i1-IQ2_XS.gguf new file mode 100644 index 0000000..910d63b --- /dev/null +++ b/Sumi-v0.5.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81778ee0ca55c81e2b76aec3d1a8053662a797bacf50241f75832962ff9a397 +size 2201473568 diff --git a/Sumi-v0.5.i1-IQ2_XXS.gguf b/Sumi-v0.5.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..858773a --- /dev/null +++ b/Sumi-v0.5.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e5848e07d0971d0cbf9b2aa0e64263079571451a2e0a5841cd774bf1e06a4d +size 1994904096 diff --git a/Sumi-v0.5.i1-IQ3_M.gguf b/Sumi-v0.5.i1-IQ3_M.gguf new file mode 100644 index 0000000..4af3a4c --- /dev/null +++ b/Sumi-v0.5.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8075c15b14b259b09aa9c5b1adb25024ed8391e0014f90fdedd33c05e9ef85e +size 3288846880 diff --git a/Sumi-v0.5.i1-IQ3_S.gguf b/Sumi-v0.5.i1-IQ3_S.gguf new file mode 100644 index 0000000..55ed338 --- /dev/null +++ b/Sumi-v0.5.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f64643bc8de6e2bbbf4767646bcf6a1b08dd0bb5e7048a183246a90b4d5976 +size 3186348576 diff --git a/Sumi-v0.5.i1-IQ3_XS.gguf b/Sumi-v0.5.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d420dd7 --- /dev/null +++ b/Sumi-v0.5.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c09534f76fa82ce69370bfdd6c97340a614eb94a0948788c63773edb56c1e65 +size 3022770720 diff --git a/Sumi-v0.5.i1-IQ3_XXS.gguf b/Sumi-v0.5.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..92fc4b2 --- /dev/null +++ b/Sumi-v0.5.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249871248f9638201245b64f53ef0efa2957cd5c4338820483d1554b55203062 +size 2830881312 diff --git a/Sumi-v0.5.i1-IQ4_XS.gguf b/Sumi-v0.5.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0bd2895 --- /dev/null +++ b/Sumi-v0.5.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a67003921ca52ea9a770c64b8756d68739800ed6beddd9bdfb36d46244b9031 +size 3911963168 diff --git a/Sumi-v0.5.i1-Q2_K.gguf b/Sumi-v0.5.i1-Q2_K.gguf new file mode 100644 index 0000000..2f87d72 --- /dev/null +++ b/Sumi-v0.5.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f65008ed5532388eab134be4081e8d2d4d8e821b2a9c95358364ab8b501928bd +size 2722877984 diff --git a/Sumi-v0.5.i1-Q2_K_S.gguf b/Sumi-v0.5.i1-Q2_K_S.gguf new file mode 100644 index 0000000..59986d5 --- /dev/null +++ b/Sumi-v0.5.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6e1e460ba65dc4b789239620ac79232a54791b9c954bc87ea1adac15a4d0b8 +size 2532561440 diff --git a/Sumi-v0.5.i1-Q3_K_L.gguf b/Sumi-v0.5.i1-Q3_K_L.gguf new file mode 100644 index 0000000..55f83d5 --- /dev/null +++ b/Sumi-v0.5.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd705d426e53dce5802c561601f9f3b6eeb0fb99b3504464f0ba184492eb25d +size 3825979936 diff --git a/Sumi-v0.5.i1-Q3_K_M.gguf b/Sumi-v0.5.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8877ff9 --- /dev/null +++ b/Sumi-v0.5.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20694e0fcbea1639410213446ba903a4e2e35df04ecc2119c59fdd014d5d9cd +size 3522941472 diff --git a/Sumi-v0.5.i1-Q3_K_S.gguf b/Sumi-v0.5.i1-Q3_K_S.gguf new file mode 100644 index 0000000..809c03e --- /dev/null +++ b/Sumi-v0.5.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbf845735d259f90a080e5ebf9504d2243fdd171ed18da76256992361cf9267 +size 3168522784 diff --git a/Sumi-v0.5.i1-Q4_0.gguf b/Sumi-v0.5.i1-Q4_0.gguf new file mode 100644 index 0000000..551a0b6 --- /dev/null +++ b/Sumi-v0.5.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f39617819871bd4c04a7633c5b881ad9063dadfabc399ca79b793824a55583d +size 4127969824 diff --git a/Sumi-v0.5.i1-Q4_K_M.gguf b/Sumi-v0.5.i1-Q4_K_M.gguf new file mode 100644 index 0000000..96cfa6a --- /dev/null +++ b/Sumi-v0.5.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96a2e7836c8b1fecff646fcc98aa4259b600e596b18012a39896474e0307c40 +size 4372812320 diff --git a/Sumi-v0.5.i1-Q4_K_S.gguf b/Sumi-v0.5.i1-Q4_K_S.gguf new file mode 100644 index 0000000..12b7af4 --- /dev/null +++ b/Sumi-v0.5.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d6322cea5464b38468782970c2b59d03ab74fa60e1006c126a744dfec8170b +size 4144747040 diff --git a/Sumi-v0.5.i1-Q5_K_M.gguf b/Sumi-v0.5.i1-Q5_K_M.gguf new file mode 100644 index 0000000..070f8da --- /dev/null +++ b/Sumi-v0.5.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e50d000958b4aef4bd7cb5458ed34c076f8aedab378f9103202f641e41ce79 +size 5136175648 diff --git a/Sumi-v0.5.i1-Q5_K_S.gguf b/Sumi-v0.5.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8409fce --- /dev/null +++ b/Sumi-v0.5.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ecdcd85becfe52c956389276c64df0202dc5ac164d32b44e9de431402b33917 +size 5002482208 diff --git a/Sumi-v0.5.i1-Q6_K.gguf b/Sumi-v0.5.i1-Q6_K.gguf new file mode 100644 index 0000000..7c4acdc --- /dev/null +++ b/Sumi-v0.5.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa134d1954560f24e9aa1e919a9e76c1e5df68616b1d7220d1ebe3a1a2209e9 +size 5947249184 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..3a929e5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e251e061daeefdf4cb022c0dcb83219a51f927e8f3a29e6a3afdb41dea84aafd +size 4988157