commit 832928c1325d4a0cc8fac3b0f450e5ffaf305c48 Author: ModelHub XC Date: Tue May 26 06:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GrammarCoder-1.3B-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e4fa5b1 --- /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-1.3B-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GrammarCoder-1.3B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GrammarCoder-1.3B-Base.IQ4_XS.gguf b/GrammarCoder-1.3B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..4886601 --- /dev/null +++ b/GrammarCoder-1.3B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c114990c2da50bd66514e2879463570bf450f8e20f557d3eebd420b22d7f134 +size 754131392 diff --git a/GrammarCoder-1.3B-Base.Q2_K.gguf b/GrammarCoder-1.3B-Base.Q2_K.gguf new file mode 100644 index 0000000..12925a0 --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0d60f2a25c3e4fbfd9d97d551df43570167f86d3520552b031e1c247c9a732 +size 562623776 diff --git a/GrammarCoder-1.3B-Base.Q3_K_L.gguf b/GrammarCoder-1.3B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..8877bfa --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8451d98a829a7629215277fa42629c0242c69b033d7d92d86ea3913d22e12521 +size 747613056 diff --git a/GrammarCoder-1.3B-Base.Q3_K_M.gguf b/GrammarCoder-1.3B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..f1d6c72 --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8946e2b937fbc27f76e29172b8b8e9d5f3d91b5dfe21104bf8b3bf7e5a4d7253 +size 707292032 diff --git a/GrammarCoder-1.3B-Base.Q3_K_S.gguf b/GrammarCoder-1.3B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..ba219e3 --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9a72db9392591c02bfcaa87a3891380567a4ad40474eb6c896af5b931e403e +size 644983680 diff --git a/GrammarCoder-1.3B-Base.Q4_K_M.gguf b/GrammarCoder-1.3B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..847e1a8 --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68bae2321067db0705c51f892a5cbd333ebacc03fe9f775e20e037bfc35cdf7c +size 876941312 diff --git a/GrammarCoder-1.3B-Base.Q4_K_S.gguf b/GrammarCoder-1.3B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..410e6da --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb7a694f00f723924603ee662dbc0e77195a743e71f0a56e12086ce451b5ed0c +size 817451008 diff --git a/GrammarCoder-1.3B-Base.Q5_K_M.gguf b/GrammarCoder-1.3B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..c5bf87d --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04b039557512331b17c5ae73bf196979d48d0fd082f5b0823dcbd94acd77e1b +size 1005635840 diff --git a/GrammarCoder-1.3B-Base.Q5_K_S.gguf b/GrammarCoder-1.3B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..2ea4def --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3686657b39b1ec9f7b73c37a4e95dde0238939c395d1b24655ff2fe5465721 +size 956680448 diff --git a/GrammarCoder-1.3B-Base.Q6_K.gguf b/GrammarCoder-1.3B-Base.Q6_K.gguf new file mode 100644 index 0000000..3ba563b --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba34848ffb93bb18d43670e452b618edc01e8d4216567bba5d520d7aaa43599f +size 1175661984 diff --git a/GrammarCoder-1.3B-Base.Q8_0.gguf b/GrammarCoder-1.3B-Base.Q8_0.gguf new file mode 100644 index 0000000..126726a --- /dev/null +++ b/GrammarCoder-1.3B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4f105a010914a2da99dbd76bdc335d03feb8eebcbbde6cae3fbb8afb046b26 +size 1437416032 diff --git a/GrammarCoder-1.3B-Base.f16.gguf b/GrammarCoder-1.3B-Base.f16.gguf new file mode 100644 index 0000000..a87925f --- /dev/null +++ b/GrammarCoder-1.3B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a39dd9a338f9f52c11cdd83ffeeadf24020e133fd1f7577c3b1cc605a933a83c +size 2704281952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..767eeeb --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: qyliang/GrammarCoder-1.3B-Base +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/qyliang/GrammarCoder-1.3B-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GrammarCoder-1.3B-Base-GGUF).*** + +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/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.IQ4_XS.gguf) | IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q5_K_S.gguf) | Q5_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.Q8_0.gguf) | Q8_0 | 1.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GrammarCoder-1.3B-Base-GGUF/resolve/main/GrammarCoder-1.3B-Base.f16.gguf) | f16 | 2.8 | 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. + +