commit 066bdf9b1b6f7cbd3f1963aa43243da206f81427 Author: ModelHub XC Date: Sun Aug 9 07:25:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..341f37d --- /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-Llama-3-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Pro-Llama-3-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ1_M.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..c4df021 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66c6308bed70cd09c2ee89f69734532e79b544d8a1a24604f188b9225695a51f +size 2162111200 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ1_S.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..9dadce8 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594b04970fb3b60aa4b87257bc21b66ec2b3afa155e10a386df49ad66e0e6066 +size 2019767008 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ2_M.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..ea794ca --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f564fb4d59467d8aa2d2e51c8c632f8ab6e886395e37b54b85a81c5a36e2e22 +size 2948433632 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ2_S.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..161930b --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95bc04b0d672a3c0861956142d59c842b180f6bb9887dd15bb144c5e1807d592 +size 2758641376 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XS.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..eb46eea --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801b165455e5b08367435a8822fc67967f6d678f5282fc23cdf6d5a5bfb44bc1 +size 2605920992 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XXS.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..080afc1 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9eacf6ee26ffa4d0d0829376fd471375ebf054ee7061dd85af86fadd3ff7523 +size 2399351520 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ3_M.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..28df7e7 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d8afe9861eeee9ac2996f8a823a9db82582e4bade007af4b5c909f0886a601 +size 3784993504 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ3_S.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..6db0fa1 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b9c16bbf9e8495d9a8eddac292a14fa6ec9195635b58bb91778ca5b0f9c934 +size 3682495200 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XS.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..653b6f8 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a144af979b2788e0b680da141fb4044e38388faefb9ef873a5c143498f61e3b7 +size 3518917344 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XXS.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..37530d9 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabbea6b9da53e10dc5d9c56c74f9b022b7f2bd0e2a3de9804c4e85bb49bfd94 +size 3275065056 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-IQ4_XS.gguf b/Hermes-2-Pro-Llama-3-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..331343a --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48bf49581763e4c3fecfe1ff51a47f9f5fb9027c3e962f23845a122c9e3af16d +size 4447846112 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q2_K.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..4729220 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ae8f8b6a23496e4eb2049318d3f31160e7b2b30ade46c9f12078bb73994e637 +size 3179288288 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_L.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4a81d2c --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71fb3a2e1dc6a75794ef5a727838fbc0398f150de79045eebb31e338b5c1362d +size 4322126560 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_M.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..fd847ee --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f1ab299f1c139672a8933131d222d82f0e8f9a9606cbca4c2934ab00d5877a +size 4019088096 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_S.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..883b255 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea6c02ca8c6d1ad8a59589f7f587583e9c1c3f2f69c87acfa386782b76bc8a45 +size 3664669408 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q4_0.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..e196031 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6999dc0e450f331b4c80ea9949be27be534a8c94415c3d1545b64a04a7707a38 +size 4676079328 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_M.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..89efd3a --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:652caebe51149e2cb9e7e0439ac81adb5d9c87f22a8a25e4ec4523d0a69fec67 +size 4920921824 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_S.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..77bb05c --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24d4b86c8af76a5b6270452156861d4ad642155365ea51eb108141e1a8f64f7 +size 4692856544 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_M.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f94d325 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60deeff293be310f2f053be4f44e2830ebb2ef953fc0900223db39bd87ed311 +size 5733191392 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_S.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0ad29a5 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2004196dde8106fd73e914ff43b0faaded4834b6bfaa997d8318460b835a5c35 +size 5599497952 diff --git a/Hermes-2-Pro-Llama-3-8B.i1-Q6_K.gguf b/Hermes-2-Pro-Llama-3-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..77756f5 --- /dev/null +++ b/Hermes-2-Pro-Llama-3-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79421a1bba3055df7a52cbcc7a06996f5594d5797c64ac2f02f2c6ea5f106266 +size 6596227808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0bfd755 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: emplitude/Hermes-2-Pro-Llama-3-8B +datasets: +- teknium/OpenHermes-2.5 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- Llama-3 +- instruct +- finetune +- chatml +- DPO +- RLHF +- gpt4 +- synthetic data +- distillation +- function calling +- json mode +- axolotl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/emplitude/Hermes-2-Pro-Llama-3-8B + + +static quants are available at https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-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-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..c8d4e1b --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4100cc8a27c0c31f280f2334ea3f11836217c3afb20bb423c68c9259cf8a271f +size 4988157