commit 7def2e2d0f90b7448285b39e3e50171f30912a30 Author: ModelHub XC Date: Wed Apr 22 10:11:00 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Yi-1.5-9B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c83adc6 --- /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 +Yi-1.5-9B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8799456 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: 01-ai/Yi-1.5-9B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + +weighted/imatrix quants of https://huggingface.co/01-ai/Yi-1.5-9B + + +static quants are available at https://huggingface.co/mradermacher/Yi-1.5-9B-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/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q2_K.gguf) | i1-Q2_K | 3.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q4_0.gguf) | i1-Q4_0 | 5.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-9B-i1-GGUF/resolve/main/Yi-1.5-9B.i1-Q6_K.gguf) | i1-Q6_K | 7.3 | 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. + + diff --git a/Yi-1.5-9B.i1-IQ1_M.gguf b/Yi-1.5-9B.i1-IQ1_M.gguf new file mode 100644 index 0000000..839c2b5 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa732bab606c143a50c3727063fdb7fb10b256bd0606c8a01f461d80478d95d +size 2181640672 diff --git a/Yi-1.5-9B.i1-IQ1_S.gguf b/Yi-1.5-9B.i1-IQ1_S.gguf new file mode 100644 index 0000000..da3ef2e --- /dev/null +++ b/Yi-1.5-9B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a418e558cc1d6ca479e58579814b06d28c6ae082d6403c4c55fd8f5e0211477b +size 2014573024 diff --git a/Yi-1.5-9B.i1-IQ2_M.gguf b/Yi-1.5-9B.i1-IQ2_M.gguf new file mode 100644 index 0000000..da2c552 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d2a54a1f221c073e07f6b9ffbfa8f1631f4c4b1b3a1fbdfca07c963117f5dd4 +size 3098112480 diff --git a/Yi-1.5-9B.i1-IQ2_S.gguf b/Yi-1.5-9B.i1-IQ2_S.gguf new file mode 100644 index 0000000..9b78188 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6020efd7f1fbef076b1f4ed023fe839d8e0a9532d9a312a327657a36a689f67 +size 2875355616 diff --git a/Yi-1.5-9B.i1-IQ2_XS.gguf b/Yi-1.5-9B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2a2a4ba --- /dev/null +++ b/Yi-1.5-9B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2427fedc59564eadce8443a8d5435a6719735cc2acc2d9a19039b8be24a05b8b +size 2708009440 diff --git a/Yi-1.5-9B.i1-IQ2_XXS.gguf b/Yi-1.5-9B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..61a1f06 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40bc451d4d291706250e9a8e5e42747034bd28699515943f7304798d3d6a85d7 +size 2460086752 diff --git a/Yi-1.5-9B.i1-IQ3_M.gguf b/Yi-1.5-9B.i1-IQ3_M.gguf new file mode 100644 index 0000000..c1c3386 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f0f6eeaf71973361e36f5c84fbfa69964da8032359e10e12875cd5913bf02d +size 4055462368 diff --git a/Yi-1.5-9B.i1-IQ3_S.gguf b/Yi-1.5-9B.i1-IQ3_S.gguf new file mode 100644 index 0000000..8449a19 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3106d4b219780b95f2e6f0ce04a60d63caae06be7759225890d2e958b4b6fb72 +size 3912577504 diff --git a/Yi-1.5-9B.i1-IQ3_XS.gguf b/Yi-1.5-9B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7ee0ec1 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ecdb5e64c2a130cc086bfb275c30067a63536fd68789ac8906b34e3de6f57b3 +size 3717935584 diff --git a/Yi-1.5-9B.i1-IQ3_XXS.gguf b/Yi-1.5-9B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..683ca31 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1057a922f2b0d89349786c4fced6c5a1429dd225f3fc541e941d8464c9a1490a +size 3474321888 diff --git a/Yi-1.5-9B.i1-IQ4_XS.gguf b/Yi-1.5-9B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..4b214a7 --- /dev/null +++ b/Yi-1.5-9B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e55e3a247bf1d9da5d0cc6cee8405c917749af6c08e40c3528c8eda3976e9c +size 4785009120 diff --git a/Yi-1.5-9B.i1-Q2_K.gguf b/Yi-1.5-9B.i1-Q2_K.gguf new file mode 100644 index 0000000..310de9e --- /dev/null +++ b/Yi-1.5-9B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a58edf971d9e83ecac8cbf2820ced94ae1cfc3c43b393e4fea71b12ee504ec +size 3354325472 diff --git a/Yi-1.5-9B.i1-Q2_K_S.gguf b/Yi-1.5-9B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..6ab8da9 --- /dev/null +++ b/Yi-1.5-9B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7d29bed578d908723ba5fa56e11328af543399da64e53fbb93519cc6c71f7b +size 3116135040 diff --git a/Yi-1.5-9B.i1-Q3_K_L.gguf b/Yi-1.5-9B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6c3ec23 --- /dev/null +++ b/Yi-1.5-9B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24bc6d529b6ce8f779ced52aa04157a0e19f1d21f2dc181912aa647d8cd8d4df +size 4690751968 diff --git a/Yi-1.5-9B.i1-Q3_K_M.gguf b/Yi-1.5-9B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8b3ccb5 --- /dev/null +++ b/Yi-1.5-9B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cafdeba701d19d19555aab7c8fde6bb29a4b311b90f4705d435f0853998f09f +size 4324405728 diff --git a/Yi-1.5-9B.i1-Q3_K_S.gguf b/Yi-1.5-9B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..fdf38c9 --- /dev/null +++ b/Yi-1.5-9B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf43d862971518eb3bb295e8e313ff75390b82eef0e31df3cea1e009e962776 +size 3899208160 diff --git a/Yi-1.5-9B.i1-Q4_0.gguf b/Yi-1.5-9B.i1-Q4_0.gguf new file mode 100644 index 0000000..d589dfe --- /dev/null +++ b/Yi-1.5-9B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691fe6933dbfe1eb85668a0ecb87a2e4d235c2d67ff1112817a55c711a246c5c +size 5053903328 diff --git a/Yi-1.5-9B.i1-Q4_K_M.gguf b/Yi-1.5-9B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0bd967c --- /dev/null +++ b/Yi-1.5-9B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623b84cc2a57be00ac103525c352517039c4d6abd8a39b11332ca370d1cc9770 +size 5328957920 diff --git a/Yi-1.5-9B.i1-Q4_K_S.gguf b/Yi-1.5-9B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..33fcec3 --- /dev/null +++ b/Yi-1.5-9B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6736a6f4ec04776581d1eec7f3df314101291fc61cab9162a1c4743e453dcb78 +size 5071860192 diff --git a/Yi-1.5-9B.i1-Q5_K_M.gguf b/Yi-1.5-9B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3f63572 --- /dev/null +++ b/Yi-1.5-9B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a64a2810e38cd1205f8cf753c6f698480a10eec5434f61a9986ccdd7f350ef0 +size 6258258400 diff --git a/Yi-1.5-9B.i1-Q5_K_S.gguf b/Yi-1.5-9B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..26e24fa --- /dev/null +++ b/Yi-1.5-9B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab9f82353dad44d18709889184df232cc581834b51aaf631a2de76195e2ed27 +size 6107853280 diff --git a/Yi-1.5-9B.i1-Q6_K.gguf b/Yi-1.5-9B.i1-Q6_K.gguf new file mode 100644 index 0000000..7d4809e --- /dev/null +++ b/Yi-1.5-9B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418796b02146f401f17869bf15a4233b59f4c4fb9dc992d51999bd96457556da +size 7245640160 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..73536da --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb5ceed82f47be609759cfe62117d058077b91aaa9ad0c48be812551d95111a +size 6843279