commit 8f0a68d9583b4509e135734093bc81d4a7005fd5 Author: ModelHub XC Date: Mon Apr 27 20:37:39 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45f8e1d --- /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-4.0-7B-A1B-Creative-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-7B-A1B-Creative-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea5d81a --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: WarlordHermes/granite-4.0-7B-A1B-Creative-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- granitemoehybrid +--- +## About + + + + + + + + + +static quants of https://huggingface.co/WarlordHermes/granite-4.0-7B-A1B-Creative-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#granite-4.0-7B-A1B-Creative-v0.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-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/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_S.gguf) | Q4_K_S | 3.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_S.gguf) | Q5_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_M.gguf) | Q5_K_M | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.Q8_0.gguf) | Q8_0 | 7.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-4.0-7B-A1B-Creative-v0.1-GGUF/resolve/main/granite-4.0-7B-A1B-Creative-v0.1.f16.gguf) | f16 | 13.5 | 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-4.0-7B-A1B-Creative-v0.1.IQ4_XS.gguf b/granite-4.0-7B-A1B-Creative-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..c8a4c39 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364a391b2b14fc86dbc43aa6f3cb87961194fd51562f1d3c40d5856653f394bd +size 3623296192 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q2_K.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q2_K.gguf new file mode 100644 index 0000000..53a7805 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabef69f43ab6529e5da9bf781c288598eaca0eba0384bf8dcfa228a4ce0f690 +size 2450850496 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_L.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..5461e09 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be983e3b6e8dd112d2f57e11c973a42e9c276781334bf5d2287a8210ec731db1 +size 3436826560 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_M.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..893464b --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fce042c1f4e5c9c8640dc5917cba0937716012b599e860188fa5061e4c235bf +size 3196374976 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_S.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..7d78ee2 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7d56f2cb402c6a8e41a637f704f61252b8ad03d1e4befd1268caa828c3977d6 +size 2914537408 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_M.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..51c882f --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2947ce22cd5466733cbce78e343fee3ee11b7c7bb8debc8bfb771d3a7297bac7 +size 4049883328 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_S.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..b64c0c3 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eab711e0c0959ce91c92aa05d3f81b55fd56bb657c0c5cd77151c9f94332ab02 +size 3821805760 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_M.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..35010b7 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa19c50f4b2e3996f43bac58e9fb38c075d99292602f358a49aeb6dc7b302f7f +size 4747780288 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_S.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..3c6400b --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62bc3a53f8e746b721f47ee5ba09a84947c7603608886901008a6e78befeae8a +size 4613877952 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q6_K.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q6_K.gguf new file mode 100644 index 0000000..a763bd5 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d52b11aad593b8fc1ad8d1af5757e0ec2a1ad69e4c253a1e01ba1ff1fcedbb3a +size 5489295808 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.Q8_0.gguf b/granite-4.0-7B-A1B-Creative-v0.1.Q8_0.gguf new file mode 100644 index 0000000..ac23ff1 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee2ad634fca7aff1b51879796e9380277b98042b4d74f31e66ad9c64995a58e +size 7103933536 diff --git a/granite-4.0-7B-A1B-Creative-v0.1.f16.gguf b/granite-4.0-7B-A1B-Creative-v0.1.f16.gguf new file mode 100644 index 0000000..4938cb2 --- /dev/null +++ b/granite-4.0-7B-A1B-Creative-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95343e04a724628d1ed5cb42c502007114d23f95787ca613bce6d33868dbb427 +size 13354144096