commit 7bc15edfef46e87b5f468185dc2fefe8112ee8b8 Author: ModelHub XC Date: Tue Jul 7 21:31:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Swallow-MS-7b-v0.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..63ef448 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +Swallow-MS-7b-v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-MS-7b-v0.1.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..62f5870 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: tokyotech-llm/Swallow-MS-7b-v0.1 +language: +- en +- ja +library_name: transformers +license: apache-2.0 +model_type: mistral +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/tokyotech-llm/Swallow-MS-7b-v0.1 + + +static quants are available at https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-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/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 1.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 2.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 4.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-v0.1-i1-GGUF/resolve/main/Swallow-MS-7b-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 6.1 | 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/Swallow-MS-7b-v0.1.i1-IQ1_M.gguf b/Swallow-MS-7b-v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..b057550 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8baec10aecaa63910c7a4f6f209adf048616926cffb896108f99d1bae07fd7 +size 1799622432 diff --git a/Swallow-MS-7b-v0.1.i1-IQ1_S.gguf b/Swallow-MS-7b-v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..5021ba4 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a764ce44d940cf0cdd816c7823708ea0799b68d682353448c689171b9f55247 +size 1657278240 diff --git a/Swallow-MS-7b-v0.1.i1-IQ2_M.gguf b/Swallow-MS-7b-v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..bff54f5 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b4ecfcd49518605e4bbce50f26755faade136a56f81ff47a49da3f98d3c540 +size 2550381856 diff --git a/Swallow-MS-7b-v0.1.i1-IQ2_S.gguf b/Swallow-MS-7b-v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..6f9f401 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff0c798b52dcb9746d57cd80df0603097bd4a803c02737d37431f4e65ca954b +size 2360589600 diff --git a/Swallow-MS-7b-v0.1.i1-IQ2_XS.gguf b/Swallow-MS-7b-v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..afdd5c1 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17620edcb7c49999862d15f4251e683738aa7cb5c904de5c6550d252794c9829 +size 2243432224 diff --git a/Swallow-MS-7b-v0.1.i1-IQ2_XXS.gguf b/Swallow-MS-7b-v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d18a44e --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47560322c1eab9727cc9917712254b7967cc12f560eb4cc8070597194394db5c +size 2036862752 diff --git a/Swallow-MS-7b-v0.1.i1-IQ3_M.gguf b/Swallow-MS-7b-v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..e0b635b --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d1c23bdfd9184064a627bcd59c522a8e3350b4f59ccacbe48a8449f76ffab5 +size 3340436256 diff --git a/Swallow-MS-7b-v0.1.i1-IQ3_S.gguf b/Swallow-MS-7b-v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..260df5b --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7955e1e18ba7bea75fdf5a2a46433285a602b0ec320b04df3136973853ce9bf +size 3237937952 diff --git a/Swallow-MS-7b-v0.1.i1-IQ3_XS.gguf b/Swallow-MS-7b-v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a9bf70e --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0011c7c8ff790d1e5c1d723e480da831a15c1e2121c150f3b4f485d2ce98d59 +size 3074360096 diff --git a/Swallow-MS-7b-v0.1.i1-IQ3_XXS.gguf b/Swallow-MS-7b-v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ac7ac76 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e675189c3dabf90544c32f9dcef9e63bcd58a9556d59354a83271b8f1b9d973 +size 2877013280 diff --git a/Swallow-MS-7b-v0.1.i1-IQ4_XS.gguf b/Swallow-MS-7b-v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..00ef5e2 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a102a80850f7f545299988aa8919019ceaf9e98c97dac635bc57ddb2bdb3fae +size 3967725856 diff --git a/Swallow-MS-7b-v0.1.i1-Q2_K.gguf b/Swallow-MS-7b-v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..7d37537 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eda43e3f0ff72097fc9fadcc0114569e5890c8ef67f08fe6b55b709d5a6a666 +size 2770294048 diff --git a/Swallow-MS-7b-v0.1.i1-Q3_K_L.gguf b/Swallow-MS-7b-v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..616650a --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b8498406c2bb99d47b4da1a670fa6f08fed31f656b734ef79362af54fc9814 +size 3877569312 diff --git a/Swallow-MS-7b-v0.1.i1-Q3_K_M.gguf b/Swallow-MS-7b-v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..677d195 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e883965755b2d5410a490864688300e696fbf7c68a7d345e4cd9e177cd60ed2 +size 3574530848 diff --git a/Swallow-MS-7b-v0.1.i1-Q3_K_S.gguf b/Swallow-MS-7b-v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..37617fc --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe5ae47f82052e18549c28f419661028714ceb603ce659909231a1e1883a33f +size 3220112160 diff --git a/Swallow-MS-7b-v0.1.i1-Q4_0.gguf b/Swallow-MS-7b-v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..3ce342d --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b98b749fec1e89b6a82fe6721b8df116220499ad0988f0b7d305b58db9f953d +size 4185016608 diff --git a/Swallow-MS-7b-v0.1.i1-Q4_K_M.gguf b/Swallow-MS-7b-v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8f37f2e --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83275174c8d49a8d539b6f6f91c8e68499a18ef7229c884dfc8965b6f8a2436 +size 4429859104 diff --git a/Swallow-MS-7b-v0.1.i1-Q4_K_S.gguf b/Swallow-MS-7b-v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c3d50a3 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4973d577bab7962081649524081982d3b2b37095264480fffe695dc0184eaad8 +size 4201793824 diff --git a/Swallow-MS-7b-v0.1.i1-Q5_K_M.gguf b/Swallow-MS-7b-v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f1d8957 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751a2b9938d139f787482c418bceb5abdde94dead1f830baa6bc1970f4bd68cc +size 5198358816 diff --git a/Swallow-MS-7b-v0.1.i1-Q5_K_S.gguf b/Swallow-MS-7b-v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3bb7bd4 --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adaf7d103b823bb533cbacaa91ed8a05f6b8a7e46afd77b2e05a9fa3c86e0c62 +size 5064665376 diff --git a/Swallow-MS-7b-v0.1.i1-Q6_K.gguf b/Swallow-MS-7b-v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..b9541ac --- /dev/null +++ b/Swallow-MS-7b-v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7109fb2121310d1ca77c01416e2cd325abf0783127735ab7e9354132b0dc3ef +size 6014889760 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..e99e2ed --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fcfc98842f3555749a863494fc1989ce9d61397e2312356f002a14853c0000e +size 4988157