commit 6290a994ec3ccb8c97d8757b7c49ad2dfee7181b Author: ModelHub XC Date: Tue Jul 7 17:46:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ayla-Light-12B-Stock-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd0fcc1 --- /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 +Ayla-Light-12B-Stock.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Ayla-Light-12B-Stock.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ayla-Light-12B-Stock.i1-IQ1_M.gguf b/Ayla-Light-12B-Stock.i1-IQ1_M.gguf new file mode 100644 index 0000000..e68e755 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137070646e2462b4407f71370da881b9d74f92cf7ba0e84a2725475d90c054a6 +size 3221628672 diff --git a/Ayla-Light-12B-Stock.i1-IQ1_S.gguf b/Ayla-Light-12B-Stock.i1-IQ1_S.gguf new file mode 100644 index 0000000..7fc5230 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2815ed8233502bea7bc394af761235ee9011fcb4b17d27ea1a841dd0f95b96e9 +size 2999215872 diff --git a/Ayla-Light-12B-Stock.i1-IQ2_M.gguf b/Ayla-Light-12B-Stock.i1-IQ2_M.gguf new file mode 100644 index 0000000..1253003 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e82a89c4be90299f2a023b1206234908cc167bd215e2a24ac33077ab63c55184 +size 4435027712 diff --git a/Ayla-Light-12B-Stock.i1-IQ2_S.gguf b/Ayla-Light-12B-Stock.i1-IQ2_S.gguf new file mode 100644 index 0000000..50b75f9 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77b1ca6331a075867703cb7a01f0aac41b48dc321e9683520e6586978cc34d33 +size 4138477312 diff --git a/Ayla-Light-12B-Stock.i1-IQ2_XS.gguf b/Ayla-Light-12B-Stock.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ca2f4ac --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29490cf68031372f4a86f5f703d703acfc64282d4f427aeb270e308b570588e3 +size 3915081472 diff --git a/Ayla-Light-12B-Stock.i1-IQ2_XXS.gguf b/Ayla-Light-12B-Stock.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1f0282c --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed8f2411f580efbc89fc0c808244ea7c714cf262ccaab2ffa8af836cff9a62e8 +size 3592316672 diff --git a/Ayla-Light-12B-Stock.i1-IQ3_M.gguf b/Ayla-Light-12B-Stock.i1-IQ3_M.gguf new file mode 100644 index 0000000..5358e12 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b673ae4c45fc2fd8b7f70a55313afa898d69c5a1e4de3631f845e7b725b9c6 +size 5722236672 diff --git a/Ayla-Light-12B-Stock.i1-IQ3_S.gguf b/Ayla-Light-12B-Stock.i1-IQ3_S.gguf new file mode 100644 index 0000000..abc6e06 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c94fa16d114e9e4396534ac06457f3f1804dfc74ed0fce5d6c20b9b05018e5f0 +size 5562083072 diff --git a/Ayla-Light-12B-Stock.i1-IQ3_XS.gguf b/Ayla-Light-12B-Stock.i1-IQ3_XS.gguf new file mode 100644 index 0000000..6c21b76 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4cbdeb46f14c529e68bd44b1cbbd4083124be7a49c1a8440d20b31dcce00705 +size 5306492672 diff --git a/Ayla-Light-12B-Stock.i1-IQ3_XXS.gguf b/Ayla-Light-12B-Stock.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..00f0f67 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc426a0afe6a94350e83f6f004787e46e7fb23dc4dad14548ed9bfa7730c0fda +size 4945389312 diff --git a/Ayla-Light-12B-Stock.i1-IQ4_NL.gguf b/Ayla-Light-12B-Stock.i1-IQ4_NL.gguf new file mode 100644 index 0000000..8e104f0 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b31f954ffd4c1b02709dba9d337188a4b5eb61157960b62b975018731243dc7 +size 7097919232 diff --git a/Ayla-Light-12B-Stock.i1-IQ4_XS.gguf b/Ayla-Light-12B-Stock.i1-IQ4_XS.gguf new file mode 100644 index 0000000..efb3112 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53dc6172311347e27571b50b3e852892f5ebb96c6b17309312a9a96aebbdae59 +size 6742714112 diff --git a/Ayla-Light-12B-Stock.i1-Q2_K.gguf b/Ayla-Light-12B-Stock.i1-Q2_K.gguf new file mode 100644 index 0000000..0fce9e9 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a36de9274b17fbbb00776fe0775328c048f3d552d2055e7cec595e619aaab0 +size 4791052032 diff --git a/Ayla-Light-12B-Stock.i1-Q2_K_S.gguf b/Ayla-Light-12B-Stock.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7a6ae8b --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e8ff9b29c26f921c43549fdbf54773ce160d336fe6b7ce94a9b10c515931d2a +size 4493682432 diff --git a/Ayla-Light-12B-Stock.i1-Q3_K_L.gguf b/Ayla-Light-12B-Stock.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1e52c81 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e11e8af04ef9a363821c6fd81ec0f8370f0f71fa788605c8333674e611293b +size 6561507072 diff --git a/Ayla-Light-12B-Stock.i1-Q3_K_M.gguf b/Ayla-Light-12B-Stock.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3d7fe73 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2929bb5a5a8590ce7239a3e2baeaf2b19e8aa0b7725a7e1ecf2af17b3bde7cac +size 6083094272 diff --git a/Ayla-Light-12B-Stock.i1-Q3_K_S.gguf b/Ayla-Light-12B-Stock.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6a398d6 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d901b33a936a7036e0759f1746b62acb899895273df0ae187d68dd4e112b03 +size 5534230272 diff --git a/Ayla-Light-12B-Stock.i1-Q4_0.gguf b/Ayla-Light-12B-Stock.i1-Q4_0.gguf new file mode 100644 index 0000000..b4f72cd --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c1b9d04b7a411c4762bb406a7ee44c2cb2dda88ada5a292f5ed5d7f724023f +size 7094642432 diff --git a/Ayla-Light-12B-Stock.i1-Q4_1.gguf b/Ayla-Light-12B-Stock.i1-Q4_1.gguf new file mode 100644 index 0000000..037e705 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57dba9235181cae342f6a26c0f38562b904166b5c8d38a8ca54846250f364ca1 +size 7795222272 diff --git a/Ayla-Light-12B-Stock.i1-Q4_K_M.gguf b/Ayla-Light-12B-Stock.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d968c51 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63cffbfff1539d07e1bab5fcd6654104f25136a1c098e9695f2addc81b38fb49 +size 7477208832 diff --git a/Ayla-Light-12B-Stock.i1-Q4_K_S.gguf b/Ayla-Light-12B-Stock.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ec26109 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afadf378cf772ee74176b01243c9c2a23479e6630914e42ea84a358cb0ce1c42 +size 7120201472 diff --git a/Ayla-Light-12B-Stock.i1-Q5_K_M.gguf b/Ayla-Light-12B-Stock.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b007168 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258823adf4b8a518dc958b22c7f4767a9a9be22a8e8a86bfd857977914ae9fed +size 8727635712 diff --git a/Ayla-Light-12B-Stock.i1-Q5_K_S.gguf b/Ayla-Light-12B-Stock.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fa3921b --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2772d5c183fb6b27792834bafee8e2cab779f19cc573c0d8dd993299e33d1784 +size 8518739712 diff --git a/Ayla-Light-12B-Stock.i1-Q6_K.gguf b/Ayla-Light-12B-Stock.i1-Q6_K.gguf new file mode 100644 index 0000000..3452892 --- /dev/null +++ b/Ayla-Light-12B-Stock.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9656847c3fb421bc246a7ac8965499e365be912c9d1cbc632877fa908b6c4981 +size 10056214272 diff --git a/README.md b/README.md new file mode 100644 index 0000000..50ecda7 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: yamatazen/Ayla-Light-12B-Stock +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/yamatazen/Ayla-Light-12B-Stock + + +static quants are available at https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-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/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ayla-Light-12B-Stock-i1-GGUF/resolve/main/Ayla-Light-12B-Stock.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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..0f88c29 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1562d70ad03faf53c916ac41fb69c01f620c1f0a6552e45cceb79cfb6da7a16d +size 7054405