commit 7534fdc7e29e67ca020640b7f8a179fd8b2bba5b Author: ModelHub XC Date: Mon Jun 15 22:56:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GWQ-9B-Preview2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..276e814 --- /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 +GWQ-9B-Preview2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.f16.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GWQ-9B-Preview2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GWQ-9B-Preview2.IQ4_XS.gguf b/GWQ-9B-Preview2.IQ4_XS.gguf new file mode 100644 index 0000000..cfce11c --- /dev/null +++ b/GWQ-9B-Preview2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48cad5c4dcd78ab40d939e8f1b0f8f7f165e4dab1552bf808a42971ed3018c55 +size 5223171840 diff --git a/GWQ-9B-Preview2.Q2_K.gguf b/GWQ-9B-Preview2.Q2_K.gguf new file mode 100644 index 0000000..1441c0c --- /dev/null +++ b/GWQ-9B-Preview2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0706380ee8f6628cbf7d585c656cad958b39550331a0d2a051b1faeac5c89a +size 3805398784 diff --git a/GWQ-9B-Preview2.Q3_K_L.gguf b/GWQ-9B-Preview2.Q3_K_L.gguf new file mode 100644 index 0000000..b040b50 --- /dev/null +++ b/GWQ-9B-Preview2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f487cd23a70868fa28a424c2f8dea40fe7629b7ccfb34d7339079d0519f9dcf +size 5132453632 diff --git a/GWQ-9B-Preview2.Q3_K_M.gguf b/GWQ-9B-Preview2.Q3_K_M.gguf new file mode 100644 index 0000000..f305ec0 --- /dev/null +++ b/GWQ-9B-Preview2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8457dc3020d2fbb6bfad9b2196ccd6a0ce83e963e9edef10970a107d96cb18f2 +size 4761782016 diff --git a/GWQ-9B-Preview2.Q3_K_S.gguf b/GWQ-9B-Preview2.Q3_K_S.gguf new file mode 100644 index 0000000..8b9e0c9 --- /dev/null +++ b/GWQ-9B-Preview2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60258801a510122bd1ac066565cc1aa7c27cc1b8f68cbc5b29f2c5ce2cf64361 +size 4337665792 diff --git a/GWQ-9B-Preview2.Q4_K_M.gguf b/GWQ-9B-Preview2.Q4_K_M.gguf new file mode 100644 index 0000000..a5bbeab --- /dev/null +++ b/GWQ-9B-Preview2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585666d2907af0fe835e33ebb97e8777e8afdc68b92ff8a75f8148cbe929d13c +size 5761058560 diff --git a/GWQ-9B-Preview2.Q4_K_S.gguf b/GWQ-9B-Preview2.Q4_K_S.gguf new file mode 100644 index 0000000..f9d8cd9 --- /dev/null +++ b/GWQ-9B-Preview2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6b61a096f2dc83cb885a356dd46b46a71a10d8cea81dfdbe30cb9a948b7eb7 +size 5478926080 diff --git a/GWQ-9B-Preview2.Q5_K_M.gguf b/GWQ-9B-Preview2.Q5_K_M.gguf new file mode 100644 index 0000000..9ec4432 --- /dev/null +++ b/GWQ-9B-Preview2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6faef19b2407c2ad167bb2a85774287504ad1fa33560c78a87dffd6f7ca92a36 +size 6647367424 diff --git a/GWQ-9B-Preview2.Q5_K_S.gguf b/GWQ-9B-Preview2.Q5_K_S.gguf new file mode 100644 index 0000000..5b884c5 --- /dev/null +++ b/GWQ-9B-Preview2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9424f25c193765d4656584495f755c1b7885391f835f9d8cb6e0c5fac00e4a +size 6483592960 diff --git a/GWQ-9B-Preview2.Q6_K.gguf b/GWQ-9B-Preview2.Q6_K.gguf new file mode 100644 index 0000000..d281e74 --- /dev/null +++ b/GWQ-9B-Preview2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7221cf0275d4f091f3d91738d42966eba3cfd5ab9cf31b3fa67e1ff433ed023 +size 7589070592 diff --git a/GWQ-9B-Preview2.Q8_0.gguf b/GWQ-9B-Preview2.Q8_0.gguf new file mode 100644 index 0000000..1375f72 --- /dev/null +++ b/GWQ-9B-Preview2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981a7a5f7d2eb2815f700541c5937c1678e87e35e36d7188e6d710840ce8b539 +size 9827149568 diff --git a/GWQ-9B-Preview2.f16.gguf b/GWQ-9B-Preview2.f16.gguf new file mode 100644 index 0000000..d373a83 --- /dev/null +++ b/GWQ-9B-Preview2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b019bb1557f8a1351b7b8eb742d73cb443523554428c1abf02d3c3309cf864d +size 18490681088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9818913 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: prithivMLmods/GWQ-9B-Preview2 +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- gemma2 +- text-generation-inference +- GWQ +- 9B +- CoT +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/GWQ-9B-Preview2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GWQ-9B-Preview2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GWQ-9B-Preview2-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/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GWQ-9B-Preview2-GGUF/resolve/main/GWQ-9B-Preview2.f16.gguf) | f16 | 18.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +