commit 69762903795887e56882f6c371520e014cba8e4e Author: ModelHub XC Date: Tue Jul 7 11:08:15 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Granite-3.3-2B-Avg-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6f3170b --- /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-Avg.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.3-2B-Avg.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Granite-3.3-2B-Avg.IQ4_XS.gguf b/Granite-3.3-2B-Avg.IQ4_XS.gguf new file mode 100644 index 0000000..c7c3355 --- /dev/null +++ b/Granite-3.3-2B-Avg.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30fa4825426652516fcac4539485f331d282d53fbc0b5fbbd9feef9a3542904 +size 1397012288 diff --git a/Granite-3.3-2B-Avg.Q2_K.gguf b/Granite-3.3-2B-Avg.Q2_K.gguf new file mode 100644 index 0000000..663eff8 --- /dev/null +++ b/Granite-3.3-2B-Avg.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e597d80d5691df560ba9f0467bb52eff895bef076006ffe7a454244805e3a5 +size 978237248 diff --git a/Granite-3.3-2B-Avg.Q3_K_L.gguf b/Granite-3.3-2B-Avg.Q3_K_L.gguf new file mode 100644 index 0000000..9fd32e1 --- /dev/null +++ b/Granite-3.3-2B-Avg.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76109ffe91719aaeb79fa73de10bd26da8437d2dd5c27445dab9fd33b7a7b432 +size 1357363008 diff --git a/Granite-3.3-2B-Avg.Q3_K_M.gguf b/Granite-3.3-2B-Avg.Q3_K_M.gguf new file mode 100644 index 0000000..15c4f9d --- /dev/null +++ b/Granite-3.3-2B-Avg.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ba230562b041dbd596373ef421f2045cd1cdb6118de9ee17d1c06c97599685 +size 1251718976 diff --git a/Granite-3.3-2B-Avg.Q3_K_S.gguf b/Granite-3.3-2B-Avg.Q3_K_S.gguf new file mode 100644 index 0000000..767baed --- /dev/null +++ b/Granite-3.3-2B-Avg.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3e49ce33c8f2597cc5f7a3acfc533a66d64bcfcf47ac6d03f9b7f495d6cf8a1 +size 1130280768 diff --git a/Granite-3.3-2B-Avg.Q4_K_M.gguf b/Granite-3.3-2B-Avg.Q4_K_M.gguf new file mode 100644 index 0000000..759b29f --- /dev/null +++ b/Granite-3.3-2B-Avg.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3616a2bcb59a99bf0b94317b76a8037d598c42a88f6b88b932d90c7391de8806 +size 1545287488 diff --git a/Granite-3.3-2B-Avg.Q4_K_S.gguf b/Granite-3.3-2B-Avg.Q4_K_S.gguf new file mode 100644 index 0000000..ac6f1f9 --- /dev/null +++ b/Granite-3.3-2B-Avg.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eac9a158a92e4af03f76064b3b316d98f11cafc2a8034fae09cdf3806d1b885 +size 1464383296 diff --git a/Granite-3.3-2B-Avg.Q5_K_M.gguf b/Granite-3.3-2B-Avg.Q5_K_M.gguf new file mode 100644 index 0000000..06f2436 --- /dev/null +++ b/Granite-3.3-2B-Avg.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c35d98bb44ec56769a03be314fcf890a6027c263bfc9e25205a75c7827a46af +size 1804810048 diff --git a/Granite-3.3-2B-Avg.Q5_K_S.gguf b/Granite-3.3-2B-Avg.Q5_K_S.gguf new file mode 100644 index 0000000..1df25d0 --- /dev/null +++ b/Granite-3.3-2B-Avg.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d4518fe95a6053a78c80c53add1a5d72f7f5fea8900d6080f6c8fe257451c8 +size 1757460288 diff --git a/Granite-3.3-2B-Avg.Q6_K.gguf b/Granite-3.3-2B-Avg.Q6_K.gguf new file mode 100644 index 0000000..2986037 --- /dev/null +++ b/Granite-3.3-2B-Avg.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905df592df27af71ae6e54f74eed93351920601970263aae7e902642d4875f92 +size 2080552768 diff --git a/Granite-3.3-2B-Avg.Q8_0.gguf b/Granite-3.3-2B-Avg.Q8_0.gguf new file mode 100644 index 0000000..586fa7f --- /dev/null +++ b/Granite-3.3-2B-Avg.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf321ea430806ae63f07f8fc349b872bdfd0a52d794567134e5c1f6660244409 +size 2694100800 diff --git a/Granite-3.3-2B-Avg.f16.gguf b/Granite-3.3-2B-Avg.f16.gguf new file mode 100644 index 0000000..64b8e59 --- /dev/null +++ b/Granite-3.3-2B-Avg.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e299f4b77e4673572e7bd00cc08ee2c1e5a178b006583e7ceee6e4a6b38ad40 +size 5069125440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0db82ad --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: powermove72/Granite-3.3-2B-Avg +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- powermove72/granite-3.3-2b-Hermes3dataset +- ibm-granite/granite-3.3-2b-instruct +--- +## About + + + + + + + + + +static quants of https://huggingface.co/powermove72/Granite-3.3-2B-Avg + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Granite-3.3-2B-Avg-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q3_K_S.gguf) | Q3_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q3_K_L.gguf) | Q3_K_L | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.IQ4_XS.gguf) | IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q4_K_S.gguf) | Q4_K_S | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q4_K_M.gguf) | Q4_K_M | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.3-2B-Avg-GGUF/resolve/main/Granite-3.3-2B-Avg.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. + +