commit 3572e4d277fa95e42a2d22461154dd0e2c029c00 Author: ModelHub XC Date: Sun Nov 1 14:18:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Orion-14B-Chat-RAG-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e4b903b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,61 @@ +*.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 +Orion-14B-Chat-RAG.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Orion-14B-Chat-RAG.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Orion-14B-Chat-RAG.i1-IQ1_M.gguf b/Orion-14B-Chat-RAG.i1-IQ1_M.gguf new file mode 100644 index 0000000..8d18dfc --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d0468754426f7a26ab838815b4a85c0544e3b7fa1d75dbbc195e03c6c28ead0 +size 3625723008 diff --git a/Orion-14B-Chat-RAG.i1-IQ1_S.gguf b/Orion-14B-Chat-RAG.i1-IQ1_S.gguf new file mode 100644 index 0000000..1ebb03a --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b87e76fd6030902c7eb86cad7f14b1abb9f022f9fd8819b038bc12b5b2b235c +size 3364603008 diff --git a/Orion-14B-Chat-RAG.i1-IQ2_M.gguf b/Orion-14B-Chat-RAG.i1-IQ2_M.gguf new file mode 100644 index 0000000..9fbb6eb --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3779f6e3405ff4e6b0b6af34ac90206611bd9acf1a722b83ddefa9282b73cd10 +size 5127895168 diff --git a/Orion-14B-Chat-RAG.i1-IQ2_S.gguf b/Orion-14B-Chat-RAG.i1-IQ2_S.gguf new file mode 100644 index 0000000..ce9fcc0 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4b5ba286956a3f7cfec26f33a238f7339f63db85229eca1b1921a42545140c +size 4779735168 diff --git a/Orion-14B-Chat-RAG.i1-IQ2_XS.gguf b/Orion-14B-Chat-RAG.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f496b11 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a0a5177cc758120e44fe8aae09d5645be4f6e5c6ce0d3d1fd772d0d4b96988 +size 4441851008 diff --git a/Orion-14B-Chat-RAG.i1-IQ2_XXS.gguf b/Orion-14B-Chat-RAG.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5806548 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e9ddf8d7c96263c25b2c29bd9a04c2999476f05fee68cf27adf6ebfcfce922 +size 4060923008 diff --git a/Orion-14B-Chat-RAG.i1-IQ3_M.gguf b/Orion-14B-Chat-RAG.i1-IQ3_M.gguf new file mode 100644 index 0000000..3f769d8 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1db573fb440e552499a46e963db9d52a13981d16dc83d68e399976a47fff7b8a +size 6734740608 diff --git a/Orion-14B-Chat-RAG.i1-IQ3_S.gguf b/Orion-14B-Chat-RAG.i1-IQ3_S.gguf new file mode 100644 index 0000000..a1b0327 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04bba02c1388e1548292eeb7e5eac6da73dfdaebd20e54ff8bcc56a481205f9 +size 6403988608 diff --git a/Orion-14B-Chat-RAG.i1-IQ3_XS.gguf b/Orion-14B-Chat-RAG.i1-IQ3_XS.gguf new file mode 100644 index 0000000..aa27f90 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3338723a3ba3a6eeb4ef4472519d30737959f20ff8480522c92c2d03cba9f7af +size 6084500608 diff --git a/Orion-14B-Chat-RAG.i1-IQ3_XXS.gguf b/Orion-14B-Chat-RAG.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..877597f --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f150c7f24e9518e4145fc35b620254e7083bb34a980f9af628abfe8868f339 +size 5625559168 diff --git a/Orion-14B-Chat-RAG.i1-IQ4_XS.gguf b/Orion-14B-Chat-RAG.i1-IQ4_XS.gguf new file mode 100644 index 0000000..40dab4e --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39f12a6b0ec51f2e5ca6e565b3f89696e2a7f79751c7f2d50881f455f8e62d0 +size 7832432768 diff --git a/Orion-14B-Chat-RAG.i1-Q2_K.gguf b/Orion-14B-Chat-RAG.i1-Q2_K.gguf new file mode 100644 index 0000000..7c47d8e --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d5d93b67df3cc3afbf3df8a8d13702e5b191d520f632621759b44e66e1079e +size 5508024448 diff --git a/Orion-14B-Chat-RAG.i1-Q2_K_S.gguf b/Orion-14B-Chat-RAG.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ba889c7 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4537f71994babdef46b74f17b0390a1f4e5b6d472dbe1beca291583b3ad5dadb +size 5067704448 diff --git a/Orion-14B-Chat-RAG.i1-Q3_K_L.gguf b/Orion-14B-Chat-RAG.i1-Q3_K_L.gguf new file mode 100644 index 0000000..44fc31f --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03717cf16167d2d6ac0281bf26bf8b45bbf5317f9005cd29146413923db1f87e +size 7755668608 diff --git a/Orion-14B-Chat-RAG.i1-Q3_K_M.gguf b/Orion-14B-Chat-RAG.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c38aa8e --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289813965ef2044d8091306754558518704c098844185826f04e2468cb704433 +size 7126523008 diff --git a/Orion-14B-Chat-RAG.i1-Q3_K_S.gguf b/Orion-14B-Chat-RAG.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e5ee916 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a255ebbdb5e8e54eb25a8efda3fe6944e331fa1765c1a7bbba63e5607d7830 +size 6403988608 diff --git a/Orion-14B-Chat-RAG.i1-Q4_0.gguf b/Orion-14B-Chat-RAG.i1-Q4_0.gguf new file mode 100644 index 0000000..8d3088d --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73bcc744ddcba6f3a632933d7ca70c79a3fa93e213911f7d84898fbeff15ae74 +size 8296530048 diff --git a/Orion-14B-Chat-RAG.i1-Q4_0_4_4.gguf b/Orion-14B-Chat-RAG.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..c8c1c99 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbd5ae6d105585491c7cbd3f16fd155e347033daef308f35b09a7db537b1096 +size 8271954048 diff --git a/Orion-14B-Chat-RAG.i1-Q4_0_4_8.gguf b/Orion-14B-Chat-RAG.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..9a16ca4 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c8b0bc9f0bff60122f99cdba5d084eb54b3fb56c9c852c7d03e1a7312a7c50 +size 8271954048 diff --git a/Orion-14B-Chat-RAG.i1-Q4_0_8_8.gguf b/Orion-14B-Chat-RAG.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..3b7f909 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8fd061dc7c7ff2db1f5a99447e281b548ae88c4e5bf7330a6b59536e3fd923 +size 8271954048 diff --git a/Orion-14B-Chat-RAG.i1-Q4_K_M.gguf b/Orion-14B-Chat-RAG.i1-Q4_K_M.gguf new file mode 100644 index 0000000..04bd4ee --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4606db20b2536a0b53231bf1e4da132467897665c60a094cfd4c0a76f7b0e1b9 +size 8812626048 diff --git a/Orion-14B-Chat-RAG.i1-Q4_K_S.gguf b/Orion-14B-Chat-RAG.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e8c02f8 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a360e680bfb687a9edeaa91bc3e7fea685240d56cdfe673afab5dcbaa99a63a8 +size 8334213248 diff --git a/Orion-14B-Chat-RAG.i1-Q5_K_M.gguf b/Orion-14B-Chat-RAG.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ca72256 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c34febccfd750a474f135123486ce762f7818c946abab37b3e0ae84c3f9394 +size 10308567168 diff --git a/Orion-14B-Chat-RAG.i1-Q5_K_S.gguf b/Orion-14B-Chat-RAG.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1e46f99 --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7238d4e8dc83370b9b5d70dc1e63ac51f43587e1ac260e3ab8f5ec43314af3c +size 10030039168 diff --git a/Orion-14B-Chat-RAG.i1-Q6_K.gguf b/Orion-14B-Chat-RAG.i1-Q6_K.gguf new file mode 100644 index 0000000..4fe7f4a --- /dev/null +++ b/Orion-14B-Chat-RAG.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2a22f9f60178d013a700f7066cb0f1158922ee84f6ae44aca39d23a8c4fb52 +size 11898004608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7fdc47 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: OrionStarAI/Orion-14B-Chat-RAG +language: +- en +- zh +- ja +- ko +library_name: transformers +quantized_by: mradermacher +tags: +- code +- model +- llm +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/OrionStarAI/Orion-14B-Chat-RAG + + +static quants are available at https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-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/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ1_S.gguf) | i1-IQ1_S | 3.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ1_M.gguf) | i1-IQ1_M | 3.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ2_S.gguf) | i1-IQ2_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ2_M.gguf) | i1-IQ2_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q2_K.gguf) | i1-Q2_K | 5.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ3_S.gguf) | i1-IQ3_S | 6.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ3_M.gguf) | i1-IQ3_M | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.4 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.4 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.4 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q4_0.gguf) | i1-Q4_0 | 8.4 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-14B-Chat-RAG-i1-GGUF/resolve/main/Orion-14B-Chat-RAG.i1-Q6_K.gguf) | i1-Q6_K | 12.0 | 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..1f1490d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5031cb6fb2b3d1ea374457a6623b5a9a6cb0a090a63e766546e65d406b6ea497 +size 7382085