From 09ed733c74efb0a9a7d5bf6669ff00c00b7430d2 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 1 May 2026 09:48:07 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/functionary-small-v3.1-GGUF Source: Original Platform --- .gitattributes | 48 ++++++++++++++++++++ README.md | 65 ++++++++++++++++++++++++++++ functionary-small-v3.1.IQ4_XS.gguf | 3 ++ functionary-small-v3.1.Q2_K.gguf | 3 ++ functionary-small-v3.1.Q3_K_L.gguf | 3 ++ functionary-small-v3.1.Q3_K_M.gguf | 3 ++ functionary-small-v3.1.Q3_K_S.gguf | 3 ++ functionary-small-v3.1.Q4_0_4_4.gguf | 3 ++ functionary-small-v3.1.Q4_K_M.gguf | 3 ++ functionary-small-v3.1.Q4_K_S.gguf | 3 ++ functionary-small-v3.1.Q5_K_M.gguf | 3 ++ functionary-small-v3.1.Q5_K_S.gguf | 3 ++ functionary-small-v3.1.Q6_K.gguf | 3 ++ functionary-small-v3.1.Q8_0.gguf | 3 ++ functionary-small-v3.1.f16.gguf | 3 ++ 15 files changed, 152 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 functionary-small-v3.1.IQ4_XS.gguf create mode 100644 functionary-small-v3.1.Q2_K.gguf create mode 100644 functionary-small-v3.1.Q3_K_L.gguf create mode 100644 functionary-small-v3.1.Q3_K_M.gguf create mode 100644 functionary-small-v3.1.Q3_K_S.gguf create mode 100644 functionary-small-v3.1.Q4_0_4_4.gguf create mode 100644 functionary-small-v3.1.Q4_K_M.gguf create mode 100644 functionary-small-v3.1.Q4_K_S.gguf create mode 100644 functionary-small-v3.1.Q5_K_M.gguf create mode 100644 functionary-small-v3.1.Q5_K_S.gguf create mode 100644 functionary-small-v3.1.Q6_K.gguf create mode 100644 functionary-small-v3.1.Q8_0.gguf create mode 100644 functionary-small-v3.1.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b44fc33 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +functionary-small-v3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +functionary-small-v3.1.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce79d81 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: meetkai/functionary-small-v3.1 +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/meetkai/functionary-small-v3.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/functionary-small-v3.1-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/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/functionary-small-v3.1-GGUF/resolve/main/functionary-small-v3.1.f16.gguf) | f16 | 16.2 | 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. 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/functionary-small-v3.1.IQ4_XS.gguf b/functionary-small-v3.1.IQ4_XS.gguf new file mode 100644 index 0000000..f5079b5 --- /dev/null +++ b/functionary-small-v3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcebcb0ad473140e46848bba5148c058e9ff2fd0813a1d2adba9ae8767c6aa11 +size 4484366400 diff --git a/functionary-small-v3.1.Q2_K.gguf b/functionary-small-v3.1.Q2_K.gguf new file mode 100644 index 0000000..7b1a88d --- /dev/null +++ b/functionary-small-v3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f862fbf95193f157138043e4c89e8ddf3a31b3ac4a71a39df8b0f39b1dfa517 +size 3179135040 diff --git a/functionary-small-v3.1.Q3_K_L.gguf b/functionary-small-v3.1.Q3_K_L.gguf new file mode 100644 index 0000000..0a0ad48 --- /dev/null +++ b/functionary-small-v3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2351b656197567434cbed67a6cac33e973ef0c9a218c60f7286b79a1a6da27ff +size 4321960000 diff --git a/functionary-small-v3.1.Q3_K_M.gguf b/functionary-small-v3.1.Q3_K_M.gguf new file mode 100644 index 0000000..6a54aff --- /dev/null +++ b/functionary-small-v3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bfa04c063710145a6df5d8ae5550de534c787bdaf311e08a23b2174119b3061 +size 4018921536 diff --git a/functionary-small-v3.1.Q3_K_S.gguf b/functionary-small-v3.1.Q3_K_S.gguf new file mode 100644 index 0000000..e6ba915 --- /dev/null +++ b/functionary-small-v3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf523fb0bca088581fc3f7151d6e10c4ad6cdfb49cf795c8a38499b33ed67920 +size 3664502848 diff --git a/functionary-small-v3.1.Q4_0_4_4.gguf b/functionary-small-v3.1.Q4_0_4_4.gguf new file mode 100644 index 0000000..3ff83cc --- /dev/null +++ b/functionary-small-v3.1.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9646d19546295c3d790390f6114dc629ab04cdfa4954209329f8fc7e7f9936f9 +size 4661215296 diff --git a/functionary-small-v3.1.Q4_K_M.gguf b/functionary-small-v3.1.Q4_K_M.gguf new file mode 100644 index 0000000..4295a0e --- /dev/null +++ b/functionary-small-v3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c2e4bd726f946cac5b06e17e366e55387c51bad623b0b6de575d579c7c82a6 +size 4920737856 diff --git a/functionary-small-v3.1.Q4_K_S.gguf b/functionary-small-v3.1.Q4_K_S.gguf new file mode 100644 index 0000000..6c3fd69 --- /dev/null +++ b/functionary-small-v3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf99b31e596648f36f342ec0bf329ce2302ab635e2980df2dc0eb46d6fd474f3 +size 4692672576 diff --git a/functionary-small-v3.1.Q5_K_M.gguf b/functionary-small-v3.1.Q5_K_M.gguf new file mode 100644 index 0000000..7444989 --- /dev/null +++ b/functionary-small-v3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7535344a60deda5dd759e409b955c6c5824ea5f04685b6b7b342739730646a9f +size 5732991040 diff --git a/functionary-small-v3.1.Q5_K_S.gguf b/functionary-small-v3.1.Q5_K_S.gguf new file mode 100644 index 0000000..8159b89 --- /dev/null +++ b/functionary-small-v3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e017544e16ae7816c2aa7ba6d3ab8a362fc92a390ab0e8fd2df567abc55f9fb +size 5599297600 diff --git a/functionary-small-v3.1.Q6_K.gguf b/functionary-small-v3.1.Q6_K.gguf new file mode 100644 index 0000000..4c9c993 --- /dev/null +++ b/functionary-small-v3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b28e2618f4197fa2981289c94db84b3f36e7b91bbec34cf0f5687c17dfa651fa +size 6596010048 diff --git a/functionary-small-v3.1.Q8_0.gguf b/functionary-small-v3.1.Q8_0.gguf new file mode 100644 index 0000000..7ccd986 --- /dev/null +++ b/functionary-small-v3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb7a2a6bd10525693594c0068c6369a1174105d249b6a009f35d3f937c264f9 +size 8540774464 diff --git a/functionary-small-v3.1.f16.gguf b/functionary-small-v3.1.f16.gguf new file mode 100644 index 0000000..f92b56f --- /dev/null +++ b/functionary-small-v3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9612eeac5457bbe2a5f21b48014f9556b9115a8c5f2f9007119733551ebfa5f6 +size 16068894784