commit ad44fe1bd2dcd1f6271d6d2de696b8682a98a0f1 Author: ModelHub XC Date: Sat May 2 13:07:37 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bfee120 --- /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 +DarkHermes3B-Humanlike-v0.2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DarkHermes3B-Humanlike-v0.2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ1_M.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ1_M.gguf new file mode 100644 index 0000000..f2b89ff --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e06608dd6d59207d4d173848ae798c5933b9af92a543d030e47c4ad1614ad0e +size 924190368 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ1_S.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ1_S.gguf new file mode 100644 index 0000000..84d1cd0 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eacc847b2f6d336ab96f1d03a05239c02466ff8dc62a7839f336dc5dd49b8ba5 +size 868157088 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ2_M.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_M.gguf new file mode 100644 index 0000000..c60159a --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80a51d2dec3a816c92d09291f7ee2f3c0eb1dd2408008e9f94396a163e87dec +size 1229031072 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ2_S.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_S.gguf new file mode 100644 index 0000000..484fd4c --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e458088b4e647d8e745ae7386499a9c01d716d226aa68ba1db105802aeb93dd +size 1154320032 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XS.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..70ae53d --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcd41a61d92cec010ef6ca2436f3c845b7aea336a13b0092b56ebb3d2c96bcb +size 1100547744 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XXS.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..25c3aec --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8316126f32437bb2ab627bfbd318057feb4d88b31df8d2e058739302d03c91af +size 1017579168 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ3_M.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_M.gguf new file mode 100644 index 0000000..c96694c --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2129d2f5fb89101410d28d285a89d58987afc8b35b1a4c79df4f937611b4b0 +size 1599668288 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ3_S.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_S.gguf new file mode 100644 index 0000000..4a47374 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ece085b7c04caea19aaaff59380e8efc14861f65f8c7d174cf013b58fc4a187 +size 1542848576 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XS.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..dd40ec6 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3228d2e42d6f8a2345db507b09e26628a06a53f9ffdfdb9640434ea7362c8a0 +size 1476788288 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XXS.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..199e505 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51deaeb9bb882d951c3b5bc57fddb83323fd97db1be615e8448e8488ffa282d +size 1348765344 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ4_NL.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cf29b2d --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c8012a19c4ed7b1d14f7c0427872e21c0277bb2814e82119aef1cfaca3c624 +size 1917190208 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-IQ4_XS.gguf b/DarkHermes3B-Humanlike-v0.2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9bdf14c --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459586128ecb1cb7f008325c4f56370b7f68c206a6660800290c731392be0a13 +size 1829109824 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q2_K.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q2_K.gguf new file mode 100644 index 0000000..a0b0465 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840c1aa847dc789b08229b4b58f71aa40c8f8c7535fc707cde3a15dfb35ca398 +size 1363935296 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q2_K_S.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..a9ac6b1 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28819a79556158ec868e086745c7ec09be8931905516b510c5a5ace6801a4569 +size 1274282048 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_L.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f0cb4dc --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca1ec1094a040e48edd805467b8263ab45c85d91e6e12f2c529ee01a4e2ee07 +size 1815347264 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_M.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1fd3c20 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f9fd95ae0446c5b08b188c78208a5180d9b14c70567b170cbf190c606b5034 +size 1687158848 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_S.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..69014d1 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b2c713ed31a5464339b06595f731edc3a9dda146ef6f7c89698c6124b2ccd5 +size 1542848576 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q4_0.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q4_0.gguf new file mode 100644 index 0000000..79d7cf7 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a652728febc812d24486a49ca9bf4ffeab7c73e674ca42d7790a80b88767231f +size 1921908800 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q4_1.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q4_1.gguf new file mode 100644 index 0000000..112933d --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef3edebff233f134bf1953d782d8a2322a19419c073d1065d12f0f3dbedbcb98 +size 2093350976 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_M.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bf58627 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa6b698d34b6d7036a75c22b5d5341e36c937693937dfd87c6b09d94df0c490 +size 2019377216 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_S.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..64b97b7 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1798f1de0f8bf8ff87b48ab05a62987e19074cda5e832fd3451f75a8a6a37e55 +size 1928200256 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_M.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..311c100 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c44ad5d0d570e783dba13416f648db0e37b7acbe6ce255076bb438f5fbdaed +size 2322153536 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_S.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7c5aaa8 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a39766ec2f2da6c19867b19eb402c8bf761556e69bbcc7b9cbe6e316e90093bd +size 2269511744 diff --git a/DarkHermes3B-Humanlike-v0.2.i1-Q6_K.gguf b/DarkHermes3B-Humanlike-v0.2.i1-Q6_K.gguf new file mode 100644 index 0000000..bebd401 --- /dev/null +++ b/DarkHermes3B-Humanlike-v0.2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00413864a1f2fd68c06a4965b47b03e2b337e31f0c85ce789c75d15bba29a197 +size 2643853376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d992bab --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: mrcuddle/DarkHermes3B-Humanlike-v0.2 +datasets: +- jondurbin/truthy-dpo-v0.1 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- axolotl +- text-generation-inference +- text-generation +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mrcuddle/DarkHermes3B-Humanlike-v0.2 + + +static quants are available at https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-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/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/DarkHermes3B-Humanlike-v0.2-i1-GGUF/resolve/main/DarkHermes3B-Humanlike-v0.2.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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..9849fb9 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597375f46d7fb46d0c6bad201ce74ef263ba685f1d96641a232c515269523bfc +size 2988377