commit 117590021ac7fd8e64c55b6ba35e2e5692191452 Author: ModelHub XC Date: Mon Apr 20 05:29:46 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Aira-2-124M-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c089021 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Aira-2-124M.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aira-2-124M.i1-IQ1_M.gguf b/Aira-2-124M.i1-IQ1_M.gguf new file mode 100644 index 0000000..355da31 --- /dev/null +++ b/Aira-2-124M.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d42877fd4b6579fa5c13a90d01d92bd2fb2b7ceacf3e0174150dc471f46a8987 +size 63725312 diff --git a/Aira-2-124M.i1-IQ1_S.gguf b/Aira-2-124M.i1-IQ1_S.gguf new file mode 100644 index 0000000..42dc9bc --- /dev/null +++ b/Aira-2-124M.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af183882ee4139f73a5c0271f095e432294dbad549a79fef5137dd582d3eea2 +size 61955840 diff --git a/Aira-2-124M.i1-IQ2_M.gguf b/Aira-2-124M.i1-IQ2_M.gguf new file mode 100644 index 0000000..a5d0eda --- /dev/null +++ b/Aira-2-124M.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab667277408bf7a59741a86406803f815a3ca50209a2d85571a2140c13aac82e +size 76769504 diff --git a/Aira-2-124M.i1-IQ2_S.gguf b/Aira-2-124M.i1-IQ2_S.gguf new file mode 100644 index 0000000..41d0bc0 --- /dev/null +++ b/Aira-2-124M.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87a7a1c84c1d8026f72e63da3876508d2d5413fe061bca8f5ac673aa96ee1136 +size 74410208 diff --git a/Aira-2-124M.i1-IQ2_XS.gguf b/Aira-2-124M.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4e8a528 --- /dev/null +++ b/Aira-2-124M.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4455bc9ff3ca969000420b980080df88927e804698a35a52e6bb4b9a813b826 +size 69254912 diff --git a/Aira-2-124M.i1-IQ2_XXS.gguf b/Aira-2-124M.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0720754 --- /dev/null +++ b/Aira-2-124M.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91df344a3a334aaf78f66eac7e5515e7c275d9da4b67064dff1a5d9177829c43 +size 66674432 diff --git a/Aira-2-124M.i1-IQ3_M.gguf b/Aira-2-124M.i1-IQ3_M.gguf new file mode 100644 index 0000000..69e6472 --- /dev/null +++ b/Aira-2-124M.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f4619e0794549986847ec978bbcc80a7bd9c45aa8fe95ba0353fca467323a3 +size 94227136 diff --git a/Aira-2-124M.i1-IQ3_S.gguf b/Aira-2-124M.i1-IQ3_S.gguf new file mode 100644 index 0000000..3310451 --- /dev/null +++ b/Aira-2-124M.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ac9991359e344e09834fc4601f6538e6efd9e17063b1f72a5a90861636ed02 +size 90153664 diff --git a/Aira-2-124M.i1-IQ3_XS.gguf b/Aira-2-124M.i1-IQ3_XS.gguf new file mode 100644 index 0000000..73da956 --- /dev/null +++ b/Aira-2-124M.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac2ca60ee04d1dee9ecca172b26791e349370a84e05aa97f01899e772db1691 +size 89158336 diff --git a/Aira-2-124M.i1-IQ3_XXS.gguf b/Aira-2-124M.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f7b58ed --- /dev/null +++ b/Aira-2-124M.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa41dce0d77dc729cc9a56b898020dd94ffd2d910a1126f90fc9483402bd7d5 +size 81377504 diff --git a/Aira-2-124M.i1-IQ4_NL.gguf b/Aira-2-124M.i1-IQ4_NL.gguf new file mode 100644 index 0000000..91299c4 --- /dev/null +++ b/Aira-2-124M.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe193296bfc456b71647a8f18c7c2747de8e06d581c12efc23e585f4ccaea34 +size 106560672 diff --git a/Aira-2-124M.i1-IQ4_XS.gguf b/Aira-2-124M.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d931b78 --- /dev/null +++ b/Aira-2-124M.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878718b7d12887ab671c453daae6b61e7c65dd7cd375ff3c7877e97f887b2343 +size 102700192 diff --git a/Aira-2-124M.i1-Q2_K.gguf b/Aira-2-124M.i1-Q2_K.gguf new file mode 100644 index 0000000..fa65f63 --- /dev/null +++ b/Aira-2-124M.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af440412a80889d20ccf988d5f7c8283db6a746f4d0ebda959a5a65fd9766de2 +size 81201376 diff --git a/Aira-2-124M.i1-Q2_K_S.gguf b/Aira-2-124M.i1-Q2_K_S.gguf new file mode 100644 index 0000000..6c07eda --- /dev/null +++ b/Aira-2-124M.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7232de276acc9363c18b3f491938e174b77a25de158ddfe6489d310cb43818 +size 78160096 diff --git a/Aira-2-124M.i1-Q3_K_L.gguf b/Aira-2-124M.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d6990ff --- /dev/null +++ b/Aira-2-124M.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35c947f7ee6b383e65098838753b6005fc2c76c03b4b1e6893401c225860a5ab +size 102097600 diff --git a/Aira-2-124M.i1-Q3_K_M.gguf b/Aira-2-124M.i1-Q3_K_M.gguf new file mode 100644 index 0000000..dd98f77 --- /dev/null +++ b/Aira-2-124M.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff91c368a3fb17d9e9f75c048074d184adb439374840de46ddb93d029282643f +size 97673920 diff --git a/Aira-2-124M.i1-Q3_K_S.gguf b/Aira-2-124M.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1207fdc --- /dev/null +++ b/Aira-2-124M.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca15beefdd48a6aa4dac11f5b1f3b08dade468bcb26829236c5c38d8d982c175 +size 90153664 diff --git a/Aira-2-124M.i1-Q4_0.gguf b/Aira-2-124M.i1-Q4_0.gguf new file mode 100644 index 0000000..355a286 --- /dev/null +++ b/Aira-2-124M.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4cff3f656d7ac8a71f340ccfe9b19f1b990e021a5062a4b5bd01e24e9f350c +size 106708128 diff --git a/Aira-2-124M.i1-Q4_1.gguf b/Aira-2-124M.i1-Q4_1.gguf new file mode 100644 index 0000000..628cd09 --- /dev/null +++ b/Aira-2-124M.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6151c2001d18d5cf074e87a9f7d9d5f148614debdf99e0e594814d52fbd13f7a +size 114281600 diff --git a/Aira-2-124M.i1-Q4_K_M.gguf b/Aira-2-124M.i1-Q4_K_M.gguf new file mode 100644 index 0000000..af865dd --- /dev/null +++ b/Aira-2-124M.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97fd0ce189da3f307b5b07449027696684d59c5ca8ff0ca752c22c10a4178e1b +size 112864416 diff --git a/Aira-2-124M.i1-Q4_K_S.gguf b/Aira-2-124M.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ffcf27e --- /dev/null +++ b/Aira-2-124M.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4ad12d8227c88e5b40dde185149899931e059956948bb314366ee68f8a44b25 +size 106855584 diff --git a/Aira-2-124M.i1-Q5_K_M.gguf b/Aira-2-124M.i1-Q5_K_M.gguf new file mode 100644 index 0000000..bfa6a92 --- /dev/null +++ b/Aira-2-124M.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc13241b53d89cc6484fcd3e58c39fe754f5f4c646afd2181657def03e8a155 +size 126702720 diff --git a/Aira-2-124M.i1-Q5_K_S.gguf b/Aira-2-124M.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a7d54ff --- /dev/null +++ b/Aira-2-124M.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c219e00ca9d11d8d8fc3923fcd7d0bd35ba7a43541b0db29ddce00d5063171cf +size 122002560 diff --git a/Aira-2-124M.i1-Q6_K.gguf b/Aira-2-124M.i1-Q6_K.gguf new file mode 100644 index 0000000..c03c058 --- /dev/null +++ b/Aira-2-124M.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc3a418051a5eea468e49df824b9c5409fc2681e7a0274888a97a98cf24c754 +size 138409568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea2b4ef --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: nicholasKluge/Aira-2-124M +datasets: +- nicholasKluge/instruct-aira-dataset +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- alignment +- instruction tuned +- text generation +- conversation +- assistant +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nicholasKluge/Aira-2-124M + + +static quants are available at https://huggingface.co/mradermacher/Aira-2-124M-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/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ1_S.gguf) | i1-IQ1_S | 0.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ1_M.gguf) | i1-IQ1_M | 0.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ2_S.gguf) | i1-IQ2_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ2_M.gguf) | i1-IQ2_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q2_K.gguf) | i1-Q2_K | 0.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ3_S.gguf) | i1-IQ3_S | 0.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ3_M.gguf) | i1-IQ3_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q4_0.gguf) | i1-Q4_0 | 0.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q4_1.gguf) | i1-Q4_1 | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-i1-GGUF/resolve/main/Aira-2-124M.i1-Q6_K.gguf) | i1-Q6_K | 0.2 | 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..022dcd5 Binary files /dev/null and b/imatrix.dat differ