commit dcb81c00bd97d829e0fec3861e49668edc566368 Author: ModelHub XC Date: Sun May 31 02:09:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Optimus-7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..29ba0a8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Optimus-7B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Optimus-7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Optimus-7B.i1-IQ1_M.gguf b/Optimus-7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..0e78433 --- /dev/null +++ b/Optimus-7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6700f7a1372973ad0f0cf10e5ca08260ef87ed611f015fe4bb2851617fa13c8 +size 1754447680 diff --git a/Optimus-7B.i1-IQ1_S.gguf b/Optimus-7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..dc74a1c --- /dev/null +++ b/Optimus-7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b606f1417ec2a73d139a7c4e81d8210ec520f002faa7271fdf5345dfcee38b4b +size 1612103488 diff --git a/Optimus-7B.i1-IQ2_M.gguf b/Optimus-7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..fd598e6 --- /dev/null +++ b/Optimus-7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ba1154af4512cfb9dfc1a591d37d0796bb31ca54e18e6908cd4e4b6d949eb1 +size 2500714304 diff --git a/Optimus-7B.i1-IQ2_S.gguf b/Optimus-7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..c68270e --- /dev/null +++ b/Optimus-7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551210ba75c0f09e6093548418d5a575d362941fde378698e2e1c7fe63c289fd +size 2310922048 diff --git a/Optimus-7B.i1-IQ2_XS.gguf b/Optimus-7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fc4f878 --- /dev/null +++ b/Optimus-7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3317a1a5e3d6dd0e2b04572e59e81c491d96b25efa061aeeb4ec7e47dec2f33a +size 2198257472 diff --git a/Optimus-7B.i1-IQ2_XXS.gguf b/Optimus-7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1a9e366 --- /dev/null +++ b/Optimus-7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9f04ad1f539ac81b8704e8ea839f0a88c73d7c33afb5bafd779869ad500457 +size 1991688000 diff --git a/Optimus-7B.i1-IQ3_M.gguf b/Optimus-7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..d22d7f8 --- /dev/null +++ b/Optimus-7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063879d98979ab8c8d987fa906b1fa3e459b1b1402b10aa399e3191bb759fff4 +size 3284893504 diff --git a/Optimus-7B.i1-IQ3_S.gguf b/Optimus-7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..8be1ea6 --- /dev/null +++ b/Optimus-7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d72fb1c239e183ee5717c9e280d983cadbc294614fb977507acc0e4ae6ed614 +size 3182395200 diff --git a/Optimus-7B.i1-IQ3_XS.gguf b/Optimus-7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..265a070 --- /dev/null +++ b/Optimus-7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb88e2b109671317cf975d344a901509584b55f1e0ef754d1b5383b052a97f2 +size 3018817344 diff --git a/Optimus-7B.i1-IQ3_XXS.gguf b/Optimus-7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5d3dd6c --- /dev/null +++ b/Optimus-7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5561da83d0b08cad49bd5b62fb1dc9a8a9cfe0a27da374a5a1a5b3ea0e95f9b2 +size 2827345728 diff --git a/Optimus-7B.i1-IQ4_NL.gguf b/Optimus-7B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..e9c1133 --- /dev/null +++ b/Optimus-7B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494c12386f5b70b3ae11481232c4eaf5c6165a6c287357d90c9d504eb40690cb +size 4125695808 diff --git a/Optimus-7B.i1-IQ4_XS.gguf b/Optimus-7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e0e2606 --- /dev/null +++ b/Optimus-7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8229cb86c310a5703b75887b0ea4ae15d39b7c49f6ca129d11240a78b0113bda +size 3907690304 diff --git a/Optimus-7B.i1-Q2_K.gguf b/Optimus-7B.i1-Q2_K.gguf new file mode 100644 index 0000000..dd0e059 --- /dev/null +++ b/Optimus-7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006ad8a02d80b9d79a0a44287c5643b56490075d115196354f85a66b9d4100e2 +size 2719244096 diff --git a/Optimus-7B.i1-Q2_K_S.gguf b/Optimus-7B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..2fc0b2d --- /dev/null +++ b/Optimus-7B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3086268f7487a173ab31fdacca53dfb00b912af1c0c2008f1d680d30bb3a615 +size 2528927552 diff --git a/Optimus-7B.i1-Q3_K_L.gguf b/Optimus-7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e20a5e0 --- /dev/null +++ b/Optimus-7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164d8d4857e21cb0da6340d1e9bb702378ecbd5744fd497a8a5dbc10c23229a4 +size 3822026560 diff --git a/Optimus-7B.i1-Q3_K_M.gguf b/Optimus-7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e550997 --- /dev/null +++ b/Optimus-7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24743bde3c40c39dd449a99f8436aed6eb7e5c6fd7e5a26af9b904e833cdb188 +size 3518988096 diff --git a/Optimus-7B.i1-Q3_K_S.gguf b/Optimus-7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..41a9306 --- /dev/null +++ b/Optimus-7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7c08e7d2f57a903fd292eebb3903b2e0c0b91f475d4dcb055715a1493bbb5f +size 3164569408 diff --git a/Optimus-7B.i1-Q4_0.gguf b/Optimus-7B.i1-Q4_0.gguf new file mode 100644 index 0000000..feb6ddd --- /dev/null +++ b/Optimus-7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da93d64ed1efc3b2a9ba8ba42452ff9ad7b30b59d3798f5c5439539098e49cb4 +size 4123598656 diff --git a/Optimus-7B.i1-Q4_1.gguf b/Optimus-7B.i1-Q4_1.gguf new file mode 100644 index 0000000..f909ac7 --- /dev/null +++ b/Optimus-7B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d97e634cff8cf27fe0a2dd5083a0d92585a7147cef5ec3c822c63b93c3088256 +size 4553318208 diff --git a/Optimus-7B.i1-Q4_K_M.gguf b/Optimus-7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..258d48f --- /dev/null +++ b/Optimus-7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abfc68a96d52a877b9c58f424f2b8c56849db1a8aa44f2e2997699a329c27217 +size 4368441152 diff --git a/Optimus-7B.i1-Q4_K_S.gguf b/Optimus-7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8accf64 --- /dev/null +++ b/Optimus-7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a112012c2b239c6e90886e7a15b7f4cecea950c073e351dd7f6de765dba4c5e +size 4140375872 diff --git a/Optimus-7B.i1-Q5_K_M.gguf b/Optimus-7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..dff2eff --- /dev/null +++ b/Optimus-7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a35a94a7e2cccdd09ceed7101679bff9d57283926e474afce391c21bbdb751 +size 5131411264 diff --git a/Optimus-7B.i1-Q5_K_S.gguf b/Optimus-7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3457b5c --- /dev/null +++ b/Optimus-7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be9863d45287d4e3ef2c0c86cee5781e3b06561916ede193642a880f2beff4e +size 4997717824 diff --git a/Optimus-7B.i1-Q6_K.gguf b/Optimus-7B.i1-Q6_K.gguf new file mode 100644 index 0000000..f2f8122 --- /dev/null +++ b/Optimus-7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:311c967fb10e5c23eb941d38e1c5d61a1cf1cce453841dc9d1c0e27012ea68e4 +size 5942067008 diff --git a/Optimus-7B.imatrix.gguf b/Optimus-7B.imatrix.gguf new file mode 100644 index 0000000..07f600a --- /dev/null +++ b/Optimus-7B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d03fd5783b5a906b001c615f6c60287eaa20270e4ea4b26432e6ed589da89c5 +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c878ec --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: Q-bert/Optimus-7B +datasets: +- meta-math/MetaMathQA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Math +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Q-bert/Optimus-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Optimus-7B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Optimus-7B-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/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q4_1.gguf) | i1-Q4_1 | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Optimus-7B-i1-GGUF/resolve/main/Optimus-7B.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. + +