commit 5d1453e1d93cf6aa397ea3117a6d1b17d379929d Author: ModelHub XC Date: Thu Aug 13 02:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/granite-20b-functioncalling-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ea17d65 --- /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 +granite-20b-functioncalling.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-20b-functioncalling.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3f611ba --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: ibm-granite/granite-20b-functioncalling +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ibm-granite/granite-20b-functioncalling + + +static quants are available at https://huggingface.co/mradermacher/granite-20b-functioncalling-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/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ1_S.gguf) | i1-IQ1_S | 4.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ1_M.gguf) | i1-IQ1_M | 5.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ2_S.gguf) | i1-IQ2_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ2_M.gguf) | i1-IQ2_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q2_K.gguf) | i1-Q2_K | 8.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ3_S.gguf) | i1-IQ3_S | 9.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ3_M.gguf) | i1-IQ3_M | 9.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q4_0.gguf) | i1-Q4_0 | 11.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-20b-functioncalling-i1-GGUF/resolve/main/granite-20b-functioncalling.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | 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/granite-20b-functioncalling.i1-IQ1_M.gguf b/granite-20b-functioncalling.i1-IQ1_M.gguf new file mode 100644 index 0000000..d9b15c0 --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce6b9404741fd6c2fe20f187fe02d63e08238be56ff6c487052263a7e6e627ca +size 4912438080 diff --git a/granite-20b-functioncalling.i1-IQ1_S.gguf b/granite-20b-functioncalling.i1-IQ1_S.gguf new file mode 100644 index 0000000..4efa56a --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15bef6a5dcb6a94bf2859004ef6015fbd63ad19d9b7dd84657a577f68a29e3a2 +size 4517698368 diff --git a/granite-20b-functioncalling.i1-IQ2_M.gguf b/granite-20b-functioncalling.i1-IQ2_M.gguf new file mode 100644 index 0000000..d25b4ce --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a0300a916d403e6e26a1d6e9a7692b8024f3ca46e2754bad3ced02b8456f84 +size 7052368704 diff --git a/granite-20b-functioncalling.i1-IQ2_S.gguf b/granite-20b-functioncalling.i1-IQ2_S.gguf new file mode 100644 index 0000000..d0ab1ad --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d570ef6872b5ba57be4e997429cece87cadf60531079cb1a25a55e6956d89f64 +size 6526049088 diff --git a/granite-20b-functioncalling.i1-IQ2_XS.gguf b/granite-20b-functioncalling.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2a820aa --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570abb69bd0cfadcc3f29357d2e5616824bd32fb142a28b725e59a384b492af1 +size 6157998912 diff --git a/granite-20b-functioncalling.i1-IQ2_XXS.gguf b/granite-20b-functioncalling.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1e2a33e --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4941a3427b50c863e4772e7e0487b38f9e615d8fc77fc63a4f94fe3d962dd713 +size 5570337600 diff --git a/granite-20b-functioncalling.i1-IQ3_M.gguf b/granite-20b-functioncalling.i1-IQ3_M.gguf new file mode 100644 index 0000000..9b86fe3 --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c41e874e92afa2a13c09458768a06a1db782c78172711caed25bc1d70315b39 +size 9587186496 diff --git a/granite-20b-functioncalling.i1-IQ3_S.gguf b/granite-20b-functioncalling.i1-IQ3_S.gguf new file mode 100644 index 0000000..1fc3838 --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109c2422a4de7327c4a18402aecb86acfa957f2d130c21593cad18b43181b794 +size 8934595392 diff --git a/granite-20b-functioncalling.i1-IQ3_XS.gguf b/granite-20b-functioncalling.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b1bd08a --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5abe5645da263c5356689c0bcb5fbc046c4973647ab4e3c6cbef96799fdbc65 +size 8658557760 diff --git a/granite-20b-functioncalling.i1-IQ3_XXS.gguf b/granite-20b-functioncalling.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b06056c --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8850ae2f2a2f318d44272cff8267134d966e61c0cff306534056d08b9a6510d +size 8062540608 diff --git a/granite-20b-functioncalling.i1-IQ4_XS.gguf b/granite-20b-functioncalling.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ad97d5a --- /dev/null +++ b/granite-20b-functioncalling.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7616385ebba084e7878c87965d5735dae4e23ef0a348da0222a68da9d63b6759 +size 10936507200 diff --git a/granite-20b-functioncalling.i1-Q2_K.gguf b/granite-20b-functioncalling.i1-Q2_K.gguf new file mode 100644 index 0000000..3aa3e5a --- /dev/null +++ b/granite-20b-functioncalling.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1489b5b9cb8e1f7e83f20e29f6ec03d55dcfbcd329b14a6c9ae6a6ad04530b0 +size 7929486144 diff --git a/granite-20b-functioncalling.i1-Q3_K_L.gguf b/granite-20b-functioncalling.i1-Q3_K_L.gguf new file mode 100644 index 0000000..48905e4 --- /dev/null +++ b/granite-20b-functioncalling.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c64d8ec6804a6844daf31de1b884066776f5d7170268d444dc220f3a015b03 +size 11736505152 diff --git a/granite-20b-functioncalling.i1-Q3_K_M.gguf b/granite-20b-functioncalling.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d87dbdd --- /dev/null +++ b/granite-20b-functioncalling.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af3db4b4e3d0db1416c38dc0f9ced81af38c9348ccaa2468f8ac324e00b0c329 +size 10566294336 diff --git a/granite-20b-functioncalling.i1-Q3_K_S.gguf b/granite-20b-functioncalling.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c5e85ab --- /dev/null +++ b/granite-20b-functioncalling.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:638f6fb6dd3dc09f27e62d2a78e2a684d35686b3d25cdcc925edf5af3610a50f +size 8934595392 diff --git a/granite-20b-functioncalling.i1-Q4_0.gguf b/granite-20b-functioncalling.i1-Q4_0.gguf new file mode 100644 index 0000000..b9c8670 --- /dev/null +++ b/granite-20b-functioncalling.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f43a46da8b91104897f47f044506ea395d3731ffd47d830619b06f79d6fd7e +size 11609103168 diff --git a/granite-20b-functioncalling.i1-Q4_K_M.gguf b/granite-20b-functioncalling.i1-Q4_K_M.gguf new file mode 100644 index 0000000..85e7f94 --- /dev/null +++ b/granite-20b-functioncalling.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02914b6f6c603659d11707531114f3d3fa4603525aff7552eb46280e2fcdbace +size 12820208448 diff --git a/granite-20b-functioncalling.i1-Q4_K_S.gguf b/granite-20b-functioncalling.i1-Q4_K_S.gguf new file mode 100644 index 0000000..71bd090 --- /dev/null +++ b/granite-20b-functioncalling.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f865f4a9bab0dfaa2554e68acc0d4df89f44d44438dc2efc3ec99a1c68682175 +size 11665726272 diff --git a/granite-20b-functioncalling.i1-Q5_K_M.gguf b/granite-20b-functioncalling.i1-Q5_K_M.gguf new file mode 100644 index 0000000..dfe02c4 --- /dev/null +++ b/granite-20b-functioncalling.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b41ef01df02078aa9eb712fa51bab131a64bf29fa7cc562c95f60088f0a911b +size 14809340736 diff --git a/granite-20b-functioncalling.i1-Q5_K_S.gguf b/granite-20b-functioncalling.i1-Q5_K_S.gguf new file mode 100644 index 0000000..bc6efa3 --- /dev/null +++ b/granite-20b-functioncalling.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea3ad860bfd0f96c8e5a2e67ad0fbb819be7cf19bef6601dcbcb54fea0db25f +size 14016371520 diff --git a/granite-20b-functioncalling.i1-Q6_K.gguf b/granite-20b-functioncalling.i1-Q6_K.gguf new file mode 100644 index 0000000..929baec --- /dev/null +++ b/granite-20b-functioncalling.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87aa0ae0c78479137547a9bc36d6935533b9472a810b45258fe9515e6615822 +size 16634256192 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..a3aa262 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43cf290ca1295b13b2a2a2390a021795154ad8d5d77bd89aa540aecd53db5221 +size 8952783