commit 972e223175f66359659262012c168db04756542e Author: ModelHub XC Date: Tue Jun 16 19:52:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-3.3-2b-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce73863 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +granite-3.3-2b-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.3-2b-base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..47db9c1 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ibm-granite/granite-3.3-2b-base +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- language +- granite-3.3 +--- +## About + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-3.3-2b-base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#granite-3.3-2b-base-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-3.3-2b-base-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/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q3_K_S.gguf) | Q3_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q3_K_L.gguf) | Q3_K_L | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.IQ4_XS.gguf) | IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q4_K_S.gguf) | Q4_K_S | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q4_K_M.gguf) | Q4_K_M | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.3-2b-base-GGUF/resolve/main/granite-3.3-2b-base.f16.gguf) | f16 | 5.2 | 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. + + diff --git a/granite-3.3-2b-base.IQ4_XS.gguf b/granite-3.3-2b-base.IQ4_XS.gguf new file mode 100644 index 0000000..0e29bf2 --- /dev/null +++ b/granite-3.3-2b-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891cc2e1fd13a0a3c7d5c9440e33199e1db63607f8e8ef6ea2cc63e681b1f583 +size 1397011680 diff --git a/granite-3.3-2b-base.Q2_K.gguf b/granite-3.3-2b-base.Q2_K.gguf new file mode 100644 index 0000000..d51b035 --- /dev/null +++ b/granite-3.3-2b-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68fdc550cc2c7f66c059cffb8e7a6b3598387b3f939497e6700fd26f9ae9976b +size 978236640 diff --git a/granite-3.3-2b-base.Q3_K_L.gguf b/granite-3.3-2b-base.Q3_K_L.gguf new file mode 100644 index 0000000..248381c --- /dev/null +++ b/granite-3.3-2b-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ef400712d1e56d2400dd928d1b61640ca99cc0ffbcac96bd38ecf17fe3180b +size 1357362400 diff --git a/granite-3.3-2b-base.Q3_K_M.gguf b/granite-3.3-2b-base.Q3_K_M.gguf new file mode 100644 index 0000000..c7ddc3b --- /dev/null +++ b/granite-3.3-2b-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f6c2da0349fadbb554cc6e91a7f1f97f6beded813900398cef4b87152858a4 +size 1251718368 diff --git a/granite-3.3-2b-base.Q3_K_S.gguf b/granite-3.3-2b-base.Q3_K_S.gguf new file mode 100644 index 0000000..d664e39 --- /dev/null +++ b/granite-3.3-2b-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df2967167762a8ce5ed16ab1862d9e0bba052f2456db634cb33d00399d7f9dd +size 1130280160 diff --git a/granite-3.3-2b-base.Q4_K_M.gguf b/granite-3.3-2b-base.Q4_K_M.gguf new file mode 100644 index 0000000..cdadbc4 --- /dev/null +++ b/granite-3.3-2b-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac97d598c9e64ad613ca80f69d767149740af3af928543623480ab12d3b78004 +size 1545286880 diff --git a/granite-3.3-2b-base.Q4_K_S.gguf b/granite-3.3-2b-base.Q4_K_S.gguf new file mode 100644 index 0000000..5ffb349 --- /dev/null +++ b/granite-3.3-2b-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6640f5f4cf76384a5471bf9808d54f853aa23421c51cc68323f91f1fb02fe9ed +size 1464382688 diff --git a/granite-3.3-2b-base.Q5_K_M.gguf b/granite-3.3-2b-base.Q5_K_M.gguf new file mode 100644 index 0000000..fddab62 --- /dev/null +++ b/granite-3.3-2b-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1a05700f0e9e5420c8a4a863d40709eefb5eab654600cdb31e7adc41f001ff +size 1804809440 diff --git a/granite-3.3-2b-base.Q5_K_S.gguf b/granite-3.3-2b-base.Q5_K_S.gguf new file mode 100644 index 0000000..fb645af --- /dev/null +++ b/granite-3.3-2b-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c8a9407af43333b7cf882131f1f72764b0fca21374e433cb14c20cb70a620e4 +size 1757459680 diff --git a/granite-3.3-2b-base.Q6_K.gguf b/granite-3.3-2b-base.Q6_K.gguf new file mode 100644 index 0000000..cb1b11b --- /dev/null +++ b/granite-3.3-2b-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548dc935ea690ca690a9ba724af917fb4b39084fa383f7cd39229e6dbf00afd5 +size 2080552160 diff --git a/granite-3.3-2b-base.Q8_0.gguf b/granite-3.3-2b-base.Q8_0.gguf new file mode 100644 index 0000000..0ce5d3c --- /dev/null +++ b/granite-3.3-2b-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76fc7773e6472bd0396a80cbaf99ed86ce31b12e60b71e6808196852b9042077 +size 2694100192 diff --git a/granite-3.3-2b-base.f16.gguf b/granite-3.3-2b-base.f16.gguf new file mode 100644 index 0000000..01b727f --- /dev/null +++ b/granite-3.3-2b-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8031b45532491f9c80a83fdac81c3cf9712a92600d616c9dc7da81728ea5955 +size 5069124832