commit 80f045a962838fb0a285db30eda7f96028d6d6d9 Author: ModelHub XC Date: Wed Sep 30 03:11:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GLM-Tulu-ChatML-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c0b33d5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +GLM-Tulu-ChatML.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GLM-Tulu-ChatML.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GLM-Tulu-ChatML.i1-IQ1_M.gguf b/GLM-Tulu-ChatML.i1-IQ1_M.gguf new file mode 100644 index 0000000..8ba35e8 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f83a36d1857452d312d98ccccc115700675720602a0a01863063251864f1bb3 +size 7907190112 diff --git a/GLM-Tulu-ChatML.i1-IQ1_S.gguf b/GLM-Tulu-ChatML.i1-IQ1_S.gguf new file mode 100644 index 0000000..9dc19d6 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f731548b2e95575433af196238cd85de2455b8ed538730bce7f444c7bfeab16 +size 7267046752 diff --git a/GLM-Tulu-ChatML.i1-IQ2_M.gguf b/GLM-Tulu-ChatML.i1-IQ2_M.gguf new file mode 100644 index 0000000..ecc8395 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34fa63619202c1b01f0fa91fa3f2f7b3eb41164deb08fad841e09ffaf201d80f +size 11271994592 diff --git a/GLM-Tulu-ChatML.i1-IQ2_S.gguf b/GLM-Tulu-ChatML.i1-IQ2_S.gguf new file mode 100644 index 0000000..6d86a90 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:845ca014ebff541a7ee1b84039e75dc78936878b22ee308eab843f7228ff57bd +size 10418470112 diff --git a/GLM-Tulu-ChatML.i1-IQ2_XS.gguf b/GLM-Tulu-ChatML.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c326d9c --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce917a8925df9b652d1bd840e1633d6d092db2d217f9d1ceef83cce7a6c0a21a +size 9899578720 diff --git a/GLM-Tulu-ChatML.i1-IQ2_XXS.gguf b/GLM-Tulu-ChatML.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c61fdc3 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c6e35eb3a6ace5ba8d4b0deca1320ef7aa06a23fc10f906fa1b22e5b5a27bd +size 8974095712 diff --git a/GLM-Tulu-ChatML.i1-IQ3_M.gguf b/GLM-Tulu-ChatML.i1-IQ3_M.gguf new file mode 100644 index 0000000..8016d0c --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53329cf29d6b481fa7ec78a9509caee17690c449d669a6f890efcf83233eec7b +size 14820256032 diff --git a/GLM-Tulu-ChatML.i1-IQ3_S.gguf b/GLM-Tulu-ChatML.i1-IQ3_S.gguf new file mode 100644 index 0000000..1f34432 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80cbde889cb34b2034e13f90c05601cacb1a70946f4e049dac64bfb1283ce53 +size 14382827808 diff --git a/GLM-Tulu-ChatML.i1-IQ3_XS.gguf b/GLM-Tulu-ChatML.i1-IQ3_XS.gguf new file mode 100644 index 0000000..940d930 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e42bc874ac939a14d5e4c88b2aaef396056eecfa5f397ef56a181ff9f820d3c4 +size 13659924768 diff --git a/GLM-Tulu-ChatML.i1-IQ3_XXS.gguf b/GLM-Tulu-ChatML.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d474c9e --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a0a3bc3a00005cc0665de46dc6d1f6b7ce3d3f765dfe126fe4db75e530d748 +size 12782681312 diff --git a/GLM-Tulu-ChatML.i1-IQ4_XS.gguf b/GLM-Tulu-ChatML.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5592da0 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbfe81b74aa39e258cd76c640acdaace15a1436f0d950f0f44fe747f77d847b +size 17597718656 diff --git a/GLM-Tulu-ChatML.i1-Q2_K.gguf b/GLM-Tulu-ChatML.i1-Q2_K.gguf new file mode 100644 index 0000000..d3afe7f --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebcecfb5d667218276e48e05c836cfb120428562960794fe92a2dfa63a95bef +size 12290789792 diff --git a/GLM-Tulu-ChatML.i1-Q2_K_S.gguf b/GLM-Tulu-ChatML.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f56ef92 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3fca9b3188ae5aea42359569f39f497ae6098f59b492b9598648f38a093585 +size 11412173216 diff --git a/GLM-Tulu-ChatML.i1-Q3_K_L.gguf b/GLM-Tulu-ChatML.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7dad353 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87e13d0da673ce6a9abaaf842ea520de4b833f72e6794612339d2b6c103533e +size 17214695712 diff --git a/GLM-Tulu-ChatML.i1-Q3_K_M.gguf b/GLM-Tulu-ChatML.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f6a12eb --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dad2520928e4bc2b4a5d8a597f56484a0e62306a3237388279dcb26dcbe58b7 +size 15888967968 diff --git a/GLM-Tulu-ChatML.i1-Q3_K_S.gguf b/GLM-Tulu-ChatML.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8225a5d --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26a1fe54acbb178f74cd5799f1c36129c00da6718016f056970b6ad61ea882e +size 14370085152 diff --git a/GLM-Tulu-ChatML.i1-Q4_0.gguf b/GLM-Tulu-ChatML.i1-Q4_0.gguf new file mode 100644 index 0000000..13bedf6 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d1513743458397ae06472b27c5f937754a2e40235a6c230b473f93ab11cbf57 +size 18633164096 diff --git a/GLM-Tulu-ChatML.i1-Q4_1.gguf b/GLM-Tulu-ChatML.i1-Q4_1.gguf new file mode 100644 index 0000000..4eba8ed --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895c97b51827c127d23d5be1aafb3f27df235a412caf0574991f98d3be02b069 +size 20548243136 diff --git a/GLM-Tulu-ChatML.i1-Q4_K_M.gguf b/GLM-Tulu-ChatML.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2ec5f1f --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a265d2d4e6e79a7d1857abb14c1bffb1129674aabea97188a2287ebb016d27 +size 19678258496 diff --git a/GLM-Tulu-ChatML.i1-Q4_K_S.gguf b/GLM-Tulu-ChatML.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ead9694 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80e30879bdc246ca391572e20273449d88c76dacc2ab8e80415323cea0d0971 +size 18695882048 diff --git a/GLM-Tulu-ChatML.i1-Q5_K_M.gguf b/GLM-Tulu-ChatML.i1-Q5_K_M.gguf new file mode 100644 index 0000000..fa84605 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26fda40965e6db274b4e734b2c72d50c707ff455c4d692f774bed720ed44f9cb +size 23095539776 diff --git a/GLM-Tulu-ChatML.i1-Q5_K_S.gguf b/GLM-Tulu-ChatML.i1-Q5_K_S.gguf new file mode 100644 index 0000000..2733314 --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e90f6f8cd463db27f627cf91869a1d867cf16871380b72c4cf2ab93da0c8f87 +size 22525253696 diff --git a/GLM-Tulu-ChatML.i1-Q6_K.gguf b/GLM-Tulu-ChatML.i1-Q6_K.gguf new file mode 100644 index 0000000..b0059ee --- /dev/null +++ b/GLM-Tulu-ChatML.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a3b2f2e6cc5c1a386529881baff845424430744b85609d95048f78eb6f7561 +size 26726401152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7697b14 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: Delta-Vector/GLM-4-32B-Tulu-Instruct +datasets: +- Delta-Vector/Hydrus-Preview-Tulu-3-SFT-Mix +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- instruct +- code +- chemistry +- GLM +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Delta-Vector/GLM-4-32B-Tulu-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GLM-Tulu-ChatML-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GLM-Tulu-ChatML-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/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q4_0.gguf) | i1-Q4_0 | 18.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q4_1.gguf) | i1-Q4_1 | 20.6 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.6 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.2 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-Tulu-ChatML-i1-GGUF/resolve/main/GLM-Tulu-ChatML.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | 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..e9978e4 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2982fc5c3934f07c089a0126742b9effc821ccee147bfd83223e0f61cc05b418 +size 13129554