commit 0b30e50accf1e6dbd3df0ef86a5437cdfb24e13f Author: ModelHub XC Date: Sat Jun 13 21:38:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/deepseek-coder-33b-instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4cfced4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-33b-instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4f6818b --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: deepseek-ai/deepseek-coder-33b-instruct +language: +- en +library_name: transformers +license: other +license_link: LICENSE +license_name: deepseek +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct + + +static quants are available at https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-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/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 7.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 7.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.0 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 11.5 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 12.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 14.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 15.1 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.0 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 19.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.1 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.6 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-coder-33b-instruct-i1-GGUF/resolve/main/deepseek-coder-33b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 27.5 | practically like static Q6_K | + +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. + + diff --git a/deepseek-coder-33b-instruct.i1-IQ1_M.gguf b/deepseek-coder-33b-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..c8a42f4 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7be771b1558fd12feb02bdfc762e1664695b9df6cf88b84010e5683f58b56ac +size 7818268416 diff --git a/deepseek-coder-33b-instruct.i1-IQ1_S.gguf b/deepseek-coder-33b-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..b3a816e --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2caa883e79001ae6f4e55e18da16d5410f480591f37213c0bca8d1a285d917bc +size 7155558144 diff --git a/deepseek-coder-33b-instruct.i1-IQ2_M.gguf b/deepseek-coder-33b-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..5dd838a --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b98f253d8335e3cc5f6154b3ef138f47198446fd39866734ee8f8a4c22d200 +size 11358859008 diff --git a/deepseek-coder-33b-instruct.i1-IQ2_S.gguf b/deepseek-coder-33b-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..190a5f7 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d73c86076b8cec31d51e09f8748342e7daa14b8b6260b9f1ce4c3bbd48b99b +size 10475245312 diff --git a/deepseek-coder-33b-instruct.i1-IQ2_XS.gguf b/deepseek-coder-33b-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2d30895 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383f01511a0a5f08819dd7d9d0dd5bf45a83a27cb570b4426996a6719468d1ec +size 9905948416 diff --git a/deepseek-coder-33b-instruct.i1-IQ2_XXS.gguf b/deepseek-coder-33b-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..84f6e5c --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef79b35954747ccdd9942974b22cb9c3e207b1a887170b064d94e91e5f05769 +size 8922785536 diff --git a/deepseek-coder-33b-instruct.i1-IQ3_M.gguf b/deepseek-coder-33b-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..2c66ee8 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9795582757fa5574d35790be3e2de33645c3671fa86e4a90733a0ab4547ad036 +size 15033247488 diff --git a/deepseek-coder-33b-instruct.i1-IQ3_S.gguf b/deepseek-coder-33b-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..cd23b16 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7a2c00cb8de6ac9b5dc96afb5ceee7b425e0d67be15679c4c7df5bcd3c8487 +size 14482214656 diff --git a/deepseek-coder-33b-instruct.i1-IQ3_XS.gguf b/deepseek-coder-33b-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..47d7873 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce550e513fcc5108d95f6a48064c227c4b37c38a36a32b8157f7fb15bca65de4 +size 13705146112 diff --git a/deepseek-coder-33b-instruct.i1-IQ3_XXS.gguf b/deepseek-coder-33b-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..20ce6a2 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2edd1b8a528aceb44ebd95bae0400b3d8e2373468ea432e12bab727ca081d2 +size 12853387008 diff --git a/deepseek-coder-33b-instruct.i1-IQ4_XS.gguf b/deepseek-coder-33b-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b127205 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:931991a2aa511b8ba162d3e17aa13b1b3759cebfc37572710fe8a1af7a655d1c +size 17855704832 diff --git a/deepseek-coder-33b-instruct.i1-Q2_K.gguf b/deepseek-coder-33b-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..4cc24f1 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6bdeeac0c3004bdf9c7faf0d82c33856ef231c14605344bd25474e3f90d335c +size 12355755776 diff --git a/deepseek-coder-33b-instruct.i1-Q3_K_L.gguf b/deepseek-coder-33b-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6021684 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:637608d2319088fba76fb3227d5018d8b0b78121a8c2df37160244492c071c0c +size 17560239872 diff --git a/deepseek-coder-33b-instruct.i1-Q3_K_M.gguf b/deepseek-coder-33b-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..69f9e94 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3226ccba55cadf0883c67cb2d614dde2276c151ced54ef0359a49646ebb222eb +size 16092004096 diff --git a/deepseek-coder-33b-instruct.i1-Q3_K_S.gguf b/deepseek-coder-33b-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ec238bd --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae233a653bba9da3353d0f444b191be382094cdfd67441cab65aef0b70ad2a4 +size 14421774080 diff --git a/deepseek-coder-33b-instruct.i1-Q4_0.gguf b/deepseek-coder-33b-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..dd20a26 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78deb4ac0a8b5f76acb69b73099af9acea3e5eed3019c8118c6ebddac7023b89 +size 18879524608 diff --git a/deepseek-coder-33b-instruct.i1-Q4_K_M.gguf b/deepseek-coder-33b-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..fe1245a --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b569ed0b9b31138b242ff2205059ac00f1212ba4d0d939e16aa9b7150c878bca +size 19940531968 diff --git a/deepseek-coder-33b-instruct.i1-Q4_K_S.gguf b/deepseek-coder-33b-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d616e79 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:996448b9d7fdf044182e9c9929ef185e60e24315577905ae28e5a4374651b7f2 +size 18943405824 diff --git a/deepseek-coder-33b-instruct.i1-Q5_K_M.gguf b/deepseek-coder-33b-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..dd8410d --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:299e37672da200997f097e88a185aeb671c311b31b59ed4880c3797f875f1b4d +size 23535771392 diff --git a/deepseek-coder-33b-instruct.i1-Q5_K_S.gguf b/deepseek-coder-33b-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..94f9941 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097f8b028d253a76e50cc74eb45f6cb1c865e1a4713c5c39f6f2279ce8ce8edd +size 22958173952 diff --git a/deepseek-coder-33b-instruct.i1-Q6_K.gguf b/deepseek-coder-33b-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..f9c4167 --- /dev/null +++ b/deepseek-coder-33b-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0761b02b3a37056e72acf5275e7e7212a4179113bc610505cc283a1d32a1ff4d +size 27355713280 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..a95302b --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150f26a6e2df4731985a7c0c7aa08d637256df12c927d49d10c419607334f196 +size 15441995