commit f4ba159d4456c8cdbde0c266b9026df31cabe0c3 Author: ModelHub XC Date: Fri May 15 08:48:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRaPE-Mini-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..323a9cf --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +GRaPE-Mini-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Mini-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRaPE-Mini-Instruct.IQ4_XS.gguf b/GRaPE-Mini-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..b91714a --- /dev/null +++ b/GRaPE-Mini-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84093ea6dec9893e1dd418a0ae8443c911f361d15003ce3e633ad4e0f982db0 +size 1557315968 diff --git a/GRaPE-Mini-Instruct.Q2_K.gguf b/GRaPE-Mini-Instruct.Q2_K.gguf new file mode 100644 index 0000000..810dd7a --- /dev/null +++ b/GRaPE-Mini-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1439710a9df356423180bcf20c029fa0ea94df7e85227200d13bfe4fd3c7ecad +size 1146798464 diff --git a/GRaPE-Mini-Instruct.Q3_K_L.gguf b/GRaPE-Mini-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..80f3c8b --- /dev/null +++ b/GRaPE-Mini-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203f970d3eba0b3c70ec7bfcb21fe87c0d33ed206f54fb7494ff7badd736e0fa +size 1533723008 diff --git a/GRaPE-Mini-Instruct.Q3_K_M.gguf b/GRaPE-Mini-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e6ec2d2 --- /dev/null +++ b/GRaPE-Mini-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:483468ccf29ffbe0788f33757584259c0bbeaf1f7003ffd49678878c4c1030b0 +size 1425719680 diff --git a/GRaPE-Mini-Instruct.Q3_K_S.gguf b/GRaPE-Mini-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..67354ad --- /dev/null +++ b/GRaPE-Mini-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78c9eaa2b316e54f9c7ccc31e05a728fa78980242f036ceb1a28c46bdebd1af +size 1300152704 diff --git a/GRaPE-Mini-Instruct.Q4_K_M.gguf b/GRaPE-Mini-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..ea6491b --- /dev/null +++ b/GRaPE-Mini-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a987fa30221dd26dd73b1aedd760eeed55158cda75b95ac68c1de94e246eac8 +size 1711849856 diff --git a/GRaPE-Mini-Instruct.Q4_K_S.gguf b/GRaPE-Mini-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..f8e37e1 --- /dev/null +++ b/GRaPE-Mini-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97511eebe93d5b22410e8d04280ddc863053f2b99c32dbe2ee9a46ffffa9f2c3 +size 1631502720 diff --git a/GRaPE-Mini-Instruct.Q5_K_M.gguf b/GRaPE-Mini-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..d6a3edc --- /dev/null +++ b/GRaPE-Mini-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6f60a74636034553e884b481cd4b00d3baa2bb345a5fbcdaa082a6e5876c6b +size 1969799552 diff --git a/GRaPE-Mini-Instruct.Q5_K_S.gguf b/GRaPE-Mini-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..3653ae2 --- /dev/null +++ b/GRaPE-Mini-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce68a3ee549e5a2a9cf0c9d163ee39dbc326e815d8e92f0e8340f444e36f4bd1 +size 1923006848 diff --git a/GRaPE-Mini-Instruct.Q6_K.gguf b/GRaPE-Mini-Instruct.Q6_K.gguf new file mode 100644 index 0000000..74f7ce5 --- /dev/null +++ b/GRaPE-Mini-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59715c6e9cc09a6e7fe6b928e856781f41a7b82f2a8ac932b23e126ca9b67b6 +size 2243871104 diff --git a/GRaPE-Mini-Instruct.Q8_0.gguf b/GRaPE-Mini-Instruct.Q8_0.gguf new file mode 100644 index 0000000..39467b1 --- /dev/null +++ b/GRaPE-Mini-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a943c896538a0674b2c42dc2b021e2e7102c5bd195ed79090ac6278b24f34ef +size 2904336768 diff --git a/GRaPE-Mini-Instruct.f16.gguf b/GRaPE-Mini-Instruct.f16.gguf new file mode 100644 index 0000000..2f91d7d --- /dev/null +++ b/GRaPE-Mini-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28d0bcff87c6032a4d9a3da9e93f7891e8b43a159d5c0a7bf726ba757f0c70e +size 5460978048 diff --git a/GRaPE-Mini-Instruct.mmproj-Q8_0.gguf b/GRaPE-Mini-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..32630a5 --- /dev/null +++ b/GRaPE-Mini-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f441ef4a370893aa73e20698e2b446edccdaa335baa911306dad4390596b1e3 +size 445053344 diff --git a/GRaPE-Mini-Instruct.mmproj-f16.gguf b/GRaPE-Mini-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..983aecc --- /dev/null +++ b/GRaPE-Mini-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99876476df282da8957391563d45aa2978619df05dc1db33b2354a4d471c5a00 +size 819394976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..05d0ca8 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: SL-AI/GRaPE-Mini-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SL-AI/GRaPE-Mini-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRaPE-Mini-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-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/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q2_K.gguf) | Q2_K | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.Q8_0.gguf) | Q8_0 | 3.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Mini-Instruct-GGUF/resolve/main/GRaPE-Mini-Instruct.f16.gguf) | f16 | 5.6 | 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. + +