commit 40ff766a3a08800f909f16d0c76a031f682d120b Author: ModelHub XC Date: Mon Jun 22 20:46:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0c4e976 --- /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 +vicuna-7b-v1.3-attention-sparsity-10.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.f16.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vicuna-7b-v1.3-attention-sparsity-10.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e33f906 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: wang7776/vicuna-7b-v1.3-attention-sparsity-10 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/wang7776/vicuna-7b-v1.3-attention-sparsity-10 + + +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/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/vicuna-7b-v1.3-attention-sparsity-10-GGUF/resolve/main/vicuna-7b-v1.3-attention-sparsity-10.f16.gguf) | f16 | 13.6 | 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. + + diff --git a/vicuna-7b-v1.3-attention-sparsity-10.IQ4_XS.gguf b/vicuna-7b-v1.3-attention-sparsity-10.IQ4_XS.gguf new file mode 100644 index 0000000..b6a3ab4 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f08da24f8adc60dda35f2c4c034df60ee879b9393564ce8c5ecc8b4483dfd6 +size 3647517344 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q2_K.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q2_K.gguf new file mode 100644 index 0000000..297c33d --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25f951219d6e35cd7ab83035f27c5950cd92e032514e259cac5dc09d7ba2349 +size 2532864672 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_L.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_L.gguf new file mode 100644 index 0000000..6de0e39 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2cd5dcc6c38b85fda9913089bfc15bb97117faadaf4250393cf549ad91f657 +size 3597111968 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_M.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_M.gguf new file mode 100644 index 0000000..d5cecf7 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2849b54b4c795058e0d63cad14f242331255bd44b1804a2a8ab75394b76e64b2 +size 3298005664 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_S.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_S.gguf new file mode 100644 index 0000000..f9510cc --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb50b8fcc5c6ecc782624381c5ede6f00435cce640d878b1b7da38824328a90 +size 2948305568 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_M.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_M.gguf new file mode 100644 index 0000000..9186e27 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b92d0b8cadd91d209eeda98b8e30e3a0c05f66994982a9483f090eb93b3e837 +size 4081005216 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_S.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_S.gguf new file mode 100644 index 0000000..b7a1fa8 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e680e0a62dba1a11bc79bf7cb63e82b20b6007d796c202a5e5401e48c5fec6 +size 3856741024 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_M.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_M.gguf new file mode 100644 index 0000000..d0bfe7a --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e54f589141e7a53cc1a876340673a90365deb03294e0e62d8422d96c4f8f34 +size 4783157920 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_S.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_S.gguf new file mode 100644 index 0000000..3ecbdf9 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609d71d24e19430e2b69c9e7ed7af90712956ac59c5e16bf4d4cf4a56ae59651 +size 4651692704 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q6_K.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q6_K.gguf new file mode 100644 index 0000000..f45ff17 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83dcfee53e6b02dcb93e810dbf6625dc6d167b75619bdc9db0cd373241279aa +size 5529195168 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.Q8_0.gguf b/vicuna-7b-v1.3-attention-sparsity-10.Q8_0.gguf new file mode 100644 index 0000000..1f86f17 --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3a7921f1138e606fb05e0e69ab9064480e5a36c7959c39e476263e1f0ce225 +size 7161090720 diff --git a/vicuna-7b-v1.3-attention-sparsity-10.f16.gguf b/vicuna-7b-v1.3-attention-sparsity-10.f16.gguf new file mode 100644 index 0000000..510cfad --- /dev/null +++ b/vicuna-7b-v1.3-attention-sparsity-10.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c98b961929e7d7c1093c461f0a5446cdc1a7df02a4f577f07ec8d227b712d6 +size 13478105760