commit 67888f71cc7096699cdff84f1b1f04dcd4089b58 Author: ModelHub XC Date: Fri May 15 05:46:58 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..924fb3a --- /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 +Hermes-2-Pro-Mixtral-4x7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_M.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..a9406b8 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70b81b71ec52091a95562cc82e101be208730d1561f9aa4c91c06f86b5586908 +size 5533128192 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_S.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..afcf3f2 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd3d456f0b69e3582b038dd741154fa8bbefcbd43f627d896bf29626e70e2848 +size 5010937344 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_M.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..4c61bcd --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c1aa65c725c4e2e34bfabc653d279b69d6d94064147fe8c1d5772a10887f0 +size 7996975616 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_S.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..227c2ee --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b717d21ed3032be3d032540e26a30c5ebc113badb1d488f970ef7410580b5756 +size 7300721152 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XS.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..cddf25a --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c12d79d28b945e08a2dadfd70e4c0f21ef503c534a618f148236319c8bbef52 +size 7116477952 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XXS.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..cf62883 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53e21feae627cb0cea744ec899339fb1a817778645851c7d613e0a005786089 +size 6403446272 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_M.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..e6c16b0 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbde94832fc75d8847d97ee4f6bca77eb167bc104ad6919534895f1c55c2d858 +size 10647375360 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_S.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..55de92c --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc6fe34da81b1778d0154c47dea48f3a8ce88599a2293d2d823350eb7aca608d +size 10451291648 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XS.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..083d00c --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24223d47062615253a1e419c225d70d585e1c39cce58b5626a940e29b6724b20 +size 9891352064 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XXS.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..25b6929 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73369f43799342996cff62a8aeeb962c7241e8fa6693cf91dc810b782deb01e1 +size 9303501312 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-IQ4_XS.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d730322 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ddfd5f8c4bc9dc39c735790f89fdab184e5a7909de5a7c16bc68df076e69c1 +size 12894167552 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q2_K.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q2_K.gguf new file mode 100644 index 0000000..449fd88 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:262f27153dfa50f1a1c98087d49c1181c7b6a3aa85da69465f8181d3a0985558 +size 8843082240 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_L.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..146a829 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5936882520355c65f0f98de7d446b76e2684b7064395351c8eb93391f249f525 +size 12544249344 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_M.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..554e723 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1966974eb3607d64987e79c33dd12f087e2fb24d6a1718960270324019cb4699 +size 11580608000 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_S.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..35d22e7 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a0a743c7b7db983fca1de8cdc24e18b79bc45135044282ea2cb3b469f42322 +size 10433465856 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_0.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_0.gguf new file mode 100644 index 0000000..7d9301e --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7231a280ce72d8c201bbd585a6a3a7d42f866169683e40c412cf5a0a342ae1b6 +size 13682602496 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_M.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..046fba6 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05fd6ee330d7a5bb54604b704065948dae0256db4bff4a159fea5374fb9cb9ae +size 14610067968 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_S.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b8c52e1 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c249c4e9218676fd98ae97e06f1d34cc4ceeb84863f1ef8d75dccbf0baf19d8d +size 13743419904 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_M.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b0b0d84 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73baeb21032ca18288dc251919928b49b9a59672403e66212de2a018f343a2bf +size 17134662144 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_S.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..70782dd --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3822edd64ff4437a7cfd12bec6c5b3e5f34f425a0764b18665fcf4fcddf3b7 +size 16626627072 diff --git a/Hermes-2-Pro-Mixtral-4x7B.i1-Q6_K.gguf b/Hermes-2-Pro-Mixtral-4x7B.i1-Q6_K.gguf new file mode 100644 index 0000000..295bf53 --- /dev/null +++ b/Hermes-2-Pro-Mixtral-4x7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff055760a4d6af9d7568c5691a4524d173340b33573d31876c5a163fa8e85180 +size 19817043456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..348181d --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: Isotonic/Hermes-2-Pro-Mixtral-4x7B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- moe +- merge +- mergekit +- lazymergekit +- NousResearch/Hermes-2-Pro-Mistral-7B +- Mixtral +- instruct +- finetune +- chatml +- DPO +- RLHF +- gpt4 +- synthetic data +- distillation +- function calling +- json mode +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Isotonic/Hermes-2-Pro-Mixtral-4x7B + + +static quants are available at https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-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/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_S.gguf) | i1-IQ1_S | 5.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_S.gguf) | i1-IQ2_S | 7.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ2_M.gguf) | i1-IQ2_M | 8.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q2_K.gguf) | i1-Q2_K | 8.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_S.gguf) | i1-IQ3_S | 10.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ3_M.gguf) | i1-IQ3_M | 10.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_0.gguf) | i1-Q4_0 | 13.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Mixtral-4x7B-i1-GGUF/resolve/main/Hermes-2-Pro-Mixtral-4x7B.i1-Q6_K.gguf) | i1-Q6_K | 19.9 | 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..f59dfd8 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a6a12d184535a858a7722a9e37fa0c062e0858dd1c13d6abdb169ea30b4d24 +size 14164883