commit af98b7aee1b740056d82bd771f80396671735716 Author: ModelHub XC Date: Fri Jun 5 01:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e5ec91 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Qwen-7B-Chat-Cantonese.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ1_M.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ1_M.gguf new file mode 100644 index 0000000..8e140b4 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdbaa0c44bc7155bfa2c25f35e3f1d74eeb6824af0343228536240275677c0a +size 2097961632 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ1_S.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ1_S.gguf new file mode 100644 index 0000000..6291f0f --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9859e7801d55067dce81f542df702cc55deb56655e0736aed03602617fc828dc +size 1962990240 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ2_M.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ2_M.gguf new file mode 100644 index 0000000..8a98457 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a6f76218bd2588ed8935897943afa3d6b72a561d6123aedccdeeaf5b54514e +size 2856635040 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ2_S.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ2_S.gguf new file mode 100644 index 0000000..71bbd3c --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e329e0e524199a858f794a256896bd3f6af0b19fd75e425db72fff9ea8b7a31 +size 2676673184 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ2_XS.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ2_XS.gguf new file mode 100644 index 0000000..44d6219 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:568b377b14c5e30e21727e3efbbd8e5b14ed25791ba1753b558598d542210c91 +size 2519653024 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ2_XXS.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5eb304a --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cceb33b643e101dc62688cd89b63bd0a50265beb4f87282d3a38b234d6925908 +size 2322913952 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ3_M.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ3_M.gguf new file mode 100644 index 0000000..33e48b6 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5306dd885e4f538499412eea4a147d3e213427ba0e4672e81628c095793b92a3 +size 3878320800 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ3_S.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ3_S.gguf new file mode 100644 index 0000000..1e49efe --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd6d31a80c2b37c9ea66268d5c34369c41343d56f11cd88a080696c61996ca98 +size 3569154720 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ3_XS.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2cb0839 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32666305c5717eef4da3eb09d1719db5f432764786309aca941fceffeacaad35 +size 3467704992 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ3_XXS.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d6f5785 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f77136ab073286aadfb6d465b55eb2759779f719b7fc627eff8f63045a53503 +size 3208104608 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ4_NL.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f1ee319 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bcf0905a565fe77afcfb5fe1be6565548d0d2ea4639e5935e5114bdbb990f22 +size 4511902368 diff --git a/Qwen-7B-Chat-Cantonese.i1-IQ4_XS.gguf b/Qwen-7B-Chat-Cantonese.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6e42dea --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542783f661863a21770f9eff6f88ce6f45d6d0df97a97984642d247de5284443 +size 4290079392 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q2_K.gguf b/Qwen-7B-Chat-Cantonese.i1-Q2_K.gguf new file mode 100644 index 0000000..3c3c2ea --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb73c5642b8fb516526ed9c8270598bc5784c546f499ba33021e1ed7703d925f +size 3049294496 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q2_K_S.gguf b/Qwen-7B-Chat-Cantonese.i1-Q2_K_S.gguf new file mode 100644 index 0000000..1f4a9c1 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1304797eae71f99aa8387bc0991c45038ccb466bc7667c39d19636e678b0b2 +size 2890500768 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q3_K_L.gguf b/Qwen-7B-Chat-Cantonese.i1-Q3_K_L.gguf new file mode 100644 index 0000000..74e82da --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6fa6507b90154e0e5fe16c2d14abb049ced91e0d0fed7cb5f5cd0a3d0841a7 +size 4293458592 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q3_K_M.gguf b/Qwen-7B-Chat-Cantonese.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f5af3f4 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5474581ceeefde486c572ba627d0eef0b39966160ef0812b4e5db4c278782924 +size 4057266848 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q3_K_S.gguf b/Qwen-7B-Chat-Cantonese.i1-Q3_K_S.gguf new file mode 100644 index 0000000..12cf247 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40762157dd219d034d57937871985fa22dcd903d461bbaf0edb4499e8e83a438 +size 3569154720 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q4_0.gguf b/Qwen-7B-Chat-Cantonese.i1-Q4_0.gguf new file mode 100644 index 0000000..f16eb40 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802c4d1fd5d050aabb2616da6140877f34a008474eb0726411e33ac482711f74 +size 4523174560 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q4_1.gguf b/Qwen-7B-Chat-Cantonese.i1-Q4_1.gguf new file mode 100644 index 0000000..5d6ccce --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4342fd07735de31db8e60a0e7be51cb3df22ecb7e4c00dcc1fbcb3212e363903 +size 4955548320 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q4_K_M.gguf b/Qwen-7B-Chat-Cantonese.i1-Q4_K_M.gguf new file mode 100644 index 0000000..79af00c --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1dd6313520bb8a9b85c51a1708874df7aafe66c1b48afe31062b780633f64ba +size 4899220128 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q4_K_S.gguf b/Qwen-7B-Chat-Cantonese.i1-Q4_K_S.gguf new file mode 100644 index 0000000..24bfc72 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9a84799e35f73d6071b4ce7500575b96b4e20a2b03eea49aeb816c140099696 +size 4534446752 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q5_K_M.gguf b/Qwen-7B-Chat-Cantonese.i1-Q5_K_M.gguf new file mode 100644 index 0000000..aa93467 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffca701c64ca147075c077ec090ead0d72f90077b8bd529752f621505bbc8667 +size 5708917408 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q5_K_S.gguf b/Qwen-7B-Chat-Cantonese.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b1d515d --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f414f935e4e65f1d31907b30082687a48eb284f9ed60c120c5cd94b0d796e0e +size 5399194272 diff --git a/Qwen-7B-Chat-Cantonese.i1-Q6_K.gguf b/Qwen-7B-Chat-Cantonese.i1-Q6_K.gguf new file mode 100644 index 0000000..482bad7 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e376648d0a7366ef2a8fcc86f1811402aae25c9ec64fa4c9a28390f14ec688 +size 6341941920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8729f30 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: stvlynn/Qwen-7B-Chat-Cantonese +datasets: +- stvlynn/Cantonese-Dialogue +language: +- zh +library_name: transformers +license: agpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Cantonese +- 廣東話 +- 粤语 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/stvlynn/Qwen-7B-Chat-Cantonese + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-7B-Chat-Cantonese-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-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/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ1_M.gguf) | i1-IQ1_M | 2.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ2_S.gguf) | i1-IQ2_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.0 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ3_S.gguf) | i1-IQ3_S | 3.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q4_1.gguf) | i1-Q4_1 | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-i1-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..cddd6cc --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b673bd9e485af0886250f56e2f356e32e83b6c991d47b6b2e46e77df604f73a3 +size 3511633