From cb163dcf2baed504e602155710aaa562f2cba34a Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 24 May 2026 18:02:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/GrammarCoder-7B-Base-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++++ GrammarCoder-7B-Base.IQ4_XS.gguf | 3 ++ GrammarCoder-7B-Base.Q2_K.gguf | 3 ++ GrammarCoder-7B-Base.Q3_K_L.gguf | 3 ++ GrammarCoder-7B-Base.Q3_K_M.gguf | 3 ++ GrammarCoder-7B-Base.Q3_K_S.gguf | 3 ++ GrammarCoder-7B-Base.Q4_K_M.gguf | 3 ++ GrammarCoder-7B-Base.Q4_K_S.gguf | 3 ++ GrammarCoder-7B-Base.Q5_K_M.gguf | 3 ++ GrammarCoder-7B-Base.Q5_K_S.gguf | 3 ++ GrammarCoder-7B-Base.Q6_K.gguf | 3 ++ GrammarCoder-7B-Base.Q8_0.gguf | 3 ++ GrammarCoder-7B-Base.f16.gguf | 3 ++ README.md | 64 ++++++++++++++++++++++++++++++++ 14 files changed, 147 insertions(+) create mode 100644 .gitattributes create mode 100644 GrammarCoder-7B-Base.IQ4_XS.gguf create mode 100644 GrammarCoder-7B-Base.Q2_K.gguf create mode 100644 GrammarCoder-7B-Base.Q3_K_L.gguf create mode 100644 GrammarCoder-7B-Base.Q3_K_M.gguf create mode 100644 GrammarCoder-7B-Base.Q3_K_S.gguf create mode 100644 GrammarCoder-7B-Base.Q4_K_M.gguf create mode 100644 GrammarCoder-7B-Base.Q4_K_S.gguf create mode 100644 GrammarCoder-7B-Base.Q5_K_M.gguf create mode 100644 GrammarCoder-7B-Base.Q5_K_S.gguf create mode 100644 GrammarCoder-7B-Base.Q6_K.gguf create mode 100644 GrammarCoder-7B-Base.Q8_0.gguf create mode 100644 GrammarCoder-7B-Base.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..047b6d8 --- /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 +GrammarCoder-7B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-7B-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GrammarCoder-7B-Base.IQ4_XS.gguf b/GrammarCoder-7B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..f284d00 --- /dev/null +++ b/GrammarCoder-7B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce623aeeedc06c22827decd73687053f206a64c98a0317f195bdf520a465d40f +size 4263142304 diff --git a/GrammarCoder-7B-Base.Q2_K.gguf b/GrammarCoder-7B-Base.Q2_K.gguf new file mode 100644 index 0000000..855ece8 --- /dev/null +++ b/GrammarCoder-7B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37f5f979db0c1ace3a78364ad1f18bafad3c465397584846ca36ae31a125119b +size 3026879584 diff --git a/GrammarCoder-7B-Base.Q3_K_L.gguf b/GrammarCoder-7B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..f8f2ea7 --- /dev/null +++ b/GrammarCoder-7B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a77ab51ebc2dc95212976e512ad53e6c3b11834ab5fd99b34886743d230ce22 +size 4100350976 diff --git a/GrammarCoder-7B-Base.Q3_K_M.gguf b/GrammarCoder-7B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..9e092f5 --- /dev/null +++ b/GrammarCoder-7B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e10f493409981e7004f3e471e30f93ab907d2f5b83065bad66098d34f1dffdbc +size 3820282880 diff --git a/GrammarCoder-7B-Base.Q3_K_S.gguf b/GrammarCoder-7B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..c7737c0 --- /dev/null +++ b/GrammarCoder-7B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7b88f39c41a02f470f32d10e8f30ee7b2a110c66bb19b1742960b2b7c22c88 +size 3504260096 diff --git a/GrammarCoder-7B-Base.Q4_K_M.gguf b/GrammarCoder-7B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..cd1d3dc --- /dev/null +++ b/GrammarCoder-7B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ecec5fa54dd4f99e3ae78dd45ceddf4ddee234489100c85a0565fbdd0ce9c71 +size 4696210464 diff --git a/GrammarCoder-7B-Base.Q4_K_S.gguf b/GrammarCoder-7B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..a489e21 --- /dev/null +++ b/GrammarCoder-7B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f05c00d19630708b7b1f30d695d4683c477cd6b01e8763a291552c698b753c +size 4470905888 diff --git a/GrammarCoder-7B-Base.Q5_K_M.gguf b/GrammarCoder-7B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..d2b75c4 --- /dev/null +++ b/GrammarCoder-7B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb331889cc21ae28b0476377b4722fcc006d8f3ea5eb6610cab2c5fdcb223bb1 +size 5459140128 diff --git a/GrammarCoder-7B-Base.Q5_K_S.gguf b/GrammarCoder-7B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..6b0a802 --- /dev/null +++ b/GrammarCoder-7B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:552b3b02179cd55fbac0654685d9fe6c78cbed9c9ccc62baab7e420e420e7b7b +size 5329485344 diff --git a/GrammarCoder-7B-Base.Q6_K.gguf b/GrammarCoder-7B-Base.Q6_K.gguf new file mode 100644 index 0000000..a3e8dac --- /dev/null +++ b/GrammarCoder-7B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9526a8063178bd2b557b792090be62ca7e2adcc829307db62e6f13a0893d547 +size 6269752896 diff --git a/GrammarCoder-7B-Base.Q8_0.gguf b/GrammarCoder-7B-Base.Q8_0.gguf new file mode 100644 index 0000000..e1ab7f5 --- /dev/null +++ b/GrammarCoder-7B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b1fd01b7fd7bb23b697e2b87e71d221f6c43b678510c3c12d585806cd5b885 +size 8118620672 diff --git a/GrammarCoder-7B-Base.f16.gguf b/GrammarCoder-7B-Base.f16.gguf new file mode 100644 index 0000000..3321b1a --- /dev/null +++ b/GrammarCoder-7B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc17d382470e75797dab4c6f616e7578c2d527c8340206da67781f96cb246bda +size 15275528192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b10fc1 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: qyliang/GrammarCoder-7B-Base +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/qyliang/GrammarCoder-7B-Base + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GrammarCoder-7B-Base-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/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q5_K_M.gguf) | Q5_K_M | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-7B-Base-GGUF/resolve/main/GrammarCoder-7B-Base.f16.gguf) | f16 | 15.4 | 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. + +