commit 917eff831cd27574a319a144a1cffc899c9e2c2e Author: ModelHub XC Date: Thu Apr 30 21:36:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e2fa6af --- /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 +ORANSight_Qwen_7B_Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ1_M.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..c5a6568 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d671edfddb93196d6a0a287f615380a25405b745b6b2e13de81f9003488fd45 +size 2042197184 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ1_S.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..ff4906c --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ef05ffd0648cb2525e555554887ec89c308f4cb337d214cf9b5e546a963d51 +size 1903668416 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ2_M.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..cde04c0 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe87196aa598af268f23cf18bf4bf70014b4519e1f6e8d30de0c002942108b1 +size 2780343488 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ2_S.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..d5b0cb7 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5312ccdc781ab977d1e3233a7164b36f171df3e5a8282be38ff2a32dff6d25 +size 2595638464 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ2_XS.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8f8aa3c --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db50705fe4edc9c5a3d166f5324315111301dcb5621fc5cdc7dae01d0238cd9 +size 2469022912 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ2_XXS.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..dae4b92 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b7466f02b0b6191930cdb5e2b14399b8c96a8f5b375ea92bb6f59868a665a5 +size 2273078464 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ3_M.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..7e29e7a --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e83a69ef2f61e057972bd7854cf42e01b0b2a5da916d36e195e8cea3cc8b91 +size 3574013120 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ3_S.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..7d47c1e --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce663b84c87ddcea5ed53e1cc9f0356635170a0626a357cdaf5cfd6306a761b +size 3499193536 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ3_XS.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8a3ad72 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0635d04ad2735fef1db5f6a6fc8c9c2fb72e0223179970b1befcd51524eafb62 +size 3346257088 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ3_XXS.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c939d34 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ee4caf824aed78de27412838caa9c44038dc24f4247ee44041784a5769cb5a +size 3114515648 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ4_NL.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..c04f352 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af3d938342747e77cc845a18ac22bb78aa3b72dab83b9b8ab77fc737be4c5c3 +size 4437814464 diff --git a/ORANSight_Qwen_7B_Instruct.i1-IQ4_XS.gguf b/ORANSight_Qwen_7B_Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b1b2f17 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b73e409db8ea4f7828b797a5cd330164ec5e05e1ad5da4d98994e7852e5aff9 +size 4218473664 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q2_K.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..eaaa2a1 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dccc7632f33c6f123f0cf1cdf8bf8df221d818d93e6a138809aed79619c56679 +size 3015941312 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q2_K_S.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..80382e6 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dd8397a00c182a9285f0e0cabee640fa19e981b85714ba42aed12c1d9879066 +size 2834074816 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q3_K_L.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7e79245 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7bb19dafc7db60a2bb2bb8a2c88cb0db37d50913a48f748175de06ab6cbb580 +size 4088460480 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q3_K_M.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e311188 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2efff539210eaa655a5da9e6f188a8ee862a3a818d5a9803cc08d2bb164b9701 +size 3808392384 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q3_K_S.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6bd12b5 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b2d5e43b561d53c253020cfc711d1d8cde3d9bc69064aa0ad8ef457552752c +size 3492369600 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q4_0.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..496eb32 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5c259f7115e45fc4207e89fea8f1da27f94e46d41a4a99a0348a8d029afc0e +size 4444122304 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q4_1.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..b2cbbc9 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18dfde2cb84b79eee157502c4247b8c8809e5dc3dbbf4028c88ac36f0a00dd38 +size 4873284800 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q4_K_M.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..31b79d5 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd37d4c7fd12236e89c8034af5b65177b65542e42c99d093c05dcae9b77e6978 +size 4683074752 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q4_K_S.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ba58779 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595d9a4a561ad9a15e492485297b2b88c72393d2e1e56f362fb19250ad7a4662 +size 4457770176 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q5_K_M.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..442f040 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63237703fcf4401e8ed91a2ac0e3018c3c1aaa3da820bc5d28211134663afa70 +size 5444832448 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q5_K_S.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..49729f4 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2543cd164d9e59e337e130d7a02129d260f0ded1a745285725ae9c6b148faf06 +size 5315177664 diff --git a/ORANSight_Qwen_7B_Instruct.i1-Q6_K.gguf b/ORANSight_Qwen_7B_Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..86ce1e0 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a9b26de78a0dfd309a17622a7c8068931977eb61ab6e1ebfa2d543a1f8e391 +size 6254200000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4f81aa8 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: NextGLab/ORANSight_Qwen_7B_Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/NextGLab/ORANSight_Qwen_7B_Instruct + + +static quants are available at https://huggingface.co/mradermacher/ORANSight_Qwen_7B_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/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.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..b39a2db --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d222f6c439556f958e8b5a273057dd546b1d2e3c5411f028614672f5c2403c99 +size 4536665