commit fe7fdd0d1e4552b8aa5fa7f5037aede438fd4a40 Author: ModelHub XC Date: Sat Oct 10 11:05:24 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/OpenHermes-Gemma-2B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..adca1ce --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +OpenHermes-Gemma-2B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-Gemma-2B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenHermes-Gemma-2B.i1-IQ1_M.gguf b/OpenHermes-Gemma-2B.i1-IQ1_M.gguf new file mode 100644 index 0000000..66104fa --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6cce24cbe74f374b61cc676c126c89a61a28a47db5ebd18f492b1ffd956907c +size 813845312 diff --git a/OpenHermes-Gemma-2B.i1-IQ1_S.gguf b/OpenHermes-Gemma-2B.i1-IQ1_S.gguf new file mode 100644 index 0000000..73bd91d --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac7d168f21e88f942770cc20f864cd7267813e763e3cc02281064fd415dd1a5 +size 770960192 diff --git a/OpenHermes-Gemma-2B.i1-IQ2_M.gguf b/OpenHermes-Gemma-2B.i1-IQ2_M.gguf new file mode 100644 index 0000000..53858b7 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94601e1d4ce17ce86bd35e72d349695db6edb7587c4b441eebe53894989fd36d +size 1019472704 diff --git a/OpenHermes-Gemma-2B.i1-IQ2_S.gguf b/OpenHermes-Gemma-2B.i1-IQ2_S.gguf new file mode 100644 index 0000000..ac82d80 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7cf3871f02086a2178fdf992b3a926b9f43ecade00cad73f458e1f41e34205b +size 962292544 diff --git a/OpenHermes-Gemma-2B.i1-IQ2_XS.gguf b/OpenHermes-Gemma-2B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..64caf3d --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c9ed060fca8ce19223146745524c524c9d6eff36898b30217841ba2945aefc +size 944859968 diff --git a/OpenHermes-Gemma-2B.i1-IQ2_XXS.gguf b/OpenHermes-Gemma-2B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f4d9367 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85419dce9f089b176b59c19a1a89bf6abbc373a3506fc07cbb1df6f17b7c3047 +size 885320512 diff --git a/OpenHermes-Gemma-2B.i1-IQ3_M.gguf b/OpenHermes-Gemma-2B.i1-IQ3_M.gguf new file mode 100644 index 0000000..1f421b7 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14099220a3ed45b018c1bdd9d41e0a7d6a7f3195b4768be5ada79e598a14ef7e +size 1308175168 diff --git a/OpenHermes-Gemma-2B.i1-IQ3_S.gguf b/OpenHermes-Gemma-2B.i1-IQ3_S.gguf new file mode 100644 index 0000000..2df413f --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc40f2b911bc06a68dc8051b3a5c25eed7808624667f7e88806f66faabfac6f9 +size 1289235264 diff --git a/OpenHermes-Gemma-2B.i1-IQ3_XS.gguf b/OpenHermes-Gemma-2B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c22f116 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f5885491119644a0430114396cf7526b6b5ea0a3983d6c99aa8b5f09018d72 +size 1244359488 diff --git a/OpenHermes-Gemma-2B.i1-IQ3_XXS.gguf b/OpenHermes-Gemma-2B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..04c0795 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9825681b0a2a384ced8779bbdd4e12bd595799822a8045549b0800d47941232a +size 1125378880 diff --git a/OpenHermes-Gemma-2B.i1-IQ4_XS.gguf b/OpenHermes-Gemma-2B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..aaf286e --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23bf4a175d6716cc37035ce51a00988ae21ef50de3ec6325653498baf88b2e3 +size 1490733888 diff --git a/OpenHermes-Gemma-2B.i1-Q2_K.gguf b/OpenHermes-Gemma-2B.i1-Q2_K.gguf new file mode 100644 index 0000000..008b009 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d0434f01ccc17ebd6c0a3fb290c37e54ad75bc4df70e2f7064896b47134428c +size 1157925696 diff --git a/OpenHermes-Gemma-2B.i1-Q2_K_S.gguf b/OpenHermes-Gemma-2B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..72fe141 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73ad29de4dd8690d352b0c3159a1f5eb465aa92bcd3a15c997c30c21a3f53f1c +size 1104644928 diff --git a/OpenHermes-Gemma-2B.i1-Q3_K_L.gguf b/OpenHermes-Gemma-2B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5d1c78a --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4770203fe286ba43365ff3a7653bff5a74cf1a7080087062370f8df0f950e918 +size 1465592640 diff --git a/OpenHermes-Gemma-2B.i1-Q3_K_M.gguf b/OpenHermes-Gemma-2B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6266739 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:130f0f1068d42c048f2b2dfe196907f20e99eb8c658f94046440a9c13e57ebbb +size 1383803712 diff --git a/OpenHermes-Gemma-2B.i1-Q3_K_S.gguf b/OpenHermes-Gemma-2B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..79d9ec3 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f33918b1b20a4d879b8beb3d073ff820d647ea21ea1526a8e6e1ca12c81c98f +size 1287981888 diff --git a/OpenHermes-Gemma-2B.i1-Q4_0.gguf b/OpenHermes-Gemma-2B.i1-Q4_0.gguf new file mode 100644 index 0000000..c8721c1 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d208d8193abdb03b5c8b2eb0ddd692d2af19205d98760239453dda559c685d +size 1555385152 diff --git a/OpenHermes-Gemma-2B.i1-Q4_K_M.gguf b/OpenHermes-Gemma-2B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d762af3 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a72d98582bb373fda6de869daa474e39047342b25cc84ad586f13dcf662df59 +size 1630264128 diff --git a/OpenHermes-Gemma-2B.i1-Q4_K_S.gguf b/OpenHermes-Gemma-2B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f84536a --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08bcdfc9e8df664c5b9ff8bee22432b90f77d73e1bcd597f27f22f9f435f1b61 +size 1559841600 diff --git a/OpenHermes-Gemma-2B.i1-Q5_K_M.gguf b/OpenHermes-Gemma-2B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9c10a5e --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0000ef4c16cb4222316a7017d9ca059d2227de41dbc2ab409980e38ba36b1d58 +size 1839651648 diff --git a/OpenHermes-Gemma-2B.i1-Q5_K_S.gguf b/OpenHermes-Gemma-2B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5ef9c75 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cdef8a146c4a155f60228ba8c854952eac96b86d998679421f57d21db9f3841 +size 1798916928 diff --git a/OpenHermes-Gemma-2B.i1-Q6_K.gguf b/OpenHermes-Gemma-2B.i1-Q6_K.gguf new file mode 100644 index 0000000..5069b63 --- /dev/null +++ b/OpenHermes-Gemma-2B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9160096e8d839545c4db66e998a5e00957332403c9da36f85b5b0e4a3fb44496 +size 2062125888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a1b71d9 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: vicgalle/OpenHermes-Gemma-2B +datasets: +- vicgalle/OpenHermesPreferences-1k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/vicgalle/OpenHermes-Gemma-2B + + +static quants are available at https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-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/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q4_0.gguf) | i1-Q4_0 | 1.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-Gemma-2B-i1-GGUF/resolve/main/OpenHermes-Gemma-2B.i1-Q6_K.gguf) | i1-Q6_K | 2.2 | 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..5f8e4e3 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82de00abf2bd393d5a22af3a0edfc321714f3a0000dfdd07d63313ba54696574 +size 2068543