commit 529d3bfb8d84d038bff9d2fa64219680d005d88a Author: ModelHub XC Date: Sat Apr 11 22:52:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aira-2-1B5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e9fb795 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-2-1B5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.f16.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aira-2-1B5.IQ3_M.gguf b/Aira-2-1B5.IQ3_M.gguf new file mode 100644 index 0000000..56d0e61 --- /dev/null +++ b/Aira-2-1B5.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73874c7912ba11bd4845d05b8dad9bf39caa450cff24add1daba17b351626c07 +size 976798624 diff --git a/Aira-2-1B5.IQ3_S.gguf b/Aira-2-1B5.IQ3_S.gguf new file mode 100644 index 0000000..6f5da9e --- /dev/null +++ b/Aira-2-1B5.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf80976fc1dff1f938a0b28c080e58bf867c9500b49f5119b2c72e24b33f0871 +size 907198624 diff --git a/Aira-2-1B5.IQ3_XS.gguf b/Aira-2-1B5.IQ3_XS.gguf new file mode 100644 index 0000000..9025109 --- /dev/null +++ b/Aira-2-1B5.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272ec790f1de433097264e5c160b6f4196a55e5d23416102ed6d29eb53e5c7c5 +size 907198624 diff --git a/Aira-2-1B5.IQ4_XS.gguf b/Aira-2-1B5.IQ4_XS.gguf new file mode 100644 index 0000000..e64c0e5 --- /dev/null +++ b/Aira-2-1B5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74449a2fa8c744ed0e28e05892b3effc209cde901e60ec00a478ef69697771d6 +size 966718624 diff --git a/Aira-2-1B5.Q2_K.gguf b/Aira-2-1B5.Q2_K.gguf new file mode 100644 index 0000000..1720bc5 --- /dev/null +++ b/Aira-2-1B5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d8542e5c1f34b54e60096fc4c755e4597363fab460111dd143bbfd233e1fcd +size 907198624 diff --git a/Aira-2-1B5.Q3_K_L.gguf b/Aira-2-1B5.Q3_K_L.gguf new file mode 100644 index 0000000..78aecf7 --- /dev/null +++ b/Aira-2-1B5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:201d5c6b5277a5eadee720aa8b1c31cc0de7cd6e803f4eb6da45f5951e0d29aa +size 1103038624 diff --git a/Aira-2-1B5.Q3_K_M.gguf b/Aira-2-1B5.Q3_K_M.gguf new file mode 100644 index 0000000..f4cdc9e --- /dev/null +++ b/Aira-2-1B5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcc6b6da6d66314e64a1d3b472aab29e8bd6f173d21f2d13a6f840eb6c46472 +size 1037758624 diff --git a/Aira-2-1B5.Q3_K_S.gguf b/Aira-2-1B5.Q3_K_S.gguf new file mode 100644 index 0000000..7932cfd --- /dev/null +++ b/Aira-2-1B5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7367ce4c120d0f5bd30d2eb55d73f507f1b049389c074c130b88f83944cbde +size 907198624 diff --git a/Aira-2-1B5.Q4_K_M.gguf b/Aira-2-1B5.Q4_K_M.gguf new file mode 100644 index 0000000..cc808b0 --- /dev/null +++ b/Aira-2-1B5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574d64cfdcd7d1deea934dfb9e01c3e6303ea32f48d4fd409a619d3e3e7bc946 +size 1191810816 diff --git a/Aira-2-1B5.Q4_K_S.gguf b/Aira-2-1B5.Q4_K_S.gguf new file mode 100644 index 0000000..8c95d4e --- /dev/null +++ b/Aira-2-1B5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3db497f642b5c1d0da1e0b124cb0948046cda13a1ad14d6c888e56b19aa021c +size 1113090816 diff --git a/Aira-2-1B5.Q5_K_M.gguf b/Aira-2-1B5.Q5_K_M.gguf new file mode 100644 index 0000000..43ed3cd --- /dev/null +++ b/Aira-2-1B5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57288085791ece8d27f7aad682e346c956413548bef769821e6d46afcccc0f26 +size 1381156928 diff --git a/Aira-2-1B5.Q5_K_S.gguf b/Aira-2-1B5.Q5_K_S.gguf new file mode 100644 index 0000000..1fe5c4c --- /dev/null +++ b/Aira-2-1B5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f0ba10e4a16cf4d152bac486b9c0484069c1dcd9d6916f7a8a27b3089acf2d +size 1233316928 diff --git a/Aira-2-1B5.Q6_K.gguf b/Aira-2-1B5.Q6_K.gguf new file mode 100644 index 0000000..6bf8a36 --- /dev/null +++ b/Aira-2-1B5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a1af6f1c668130dfa4af866b9764da0d036f7061c074f6ddefe4e783960f25 +size 1630927424 diff --git a/Aira-2-1B5.Q8_0.gguf b/Aira-2-1B5.Q8_0.gguf new file mode 100644 index 0000000..653fb4c --- /dev/null +++ b/Aira-2-1B5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d5dfe583f878abc7e79ff798093b89c42f8b23e3867057714db67f096fd61c +size 1749967424 diff --git a/Aira-2-1B5.f16.gguf b/Aira-2-1B5.f16.gguf new file mode 100644 index 0000000..747a7cb --- /dev/null +++ b/Aira-2-1B5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9938d915906b1c2cfad957017e6648fc445464acac290f2136f2438f491aed0 +size 3283150400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7560901 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: nicholasKluge/Aira-2-1B5 +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 + + + + + + +static quants of https://huggingface.co/nicholasKluge/Aira-2-1B5 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ3_S.gguf) | IQ3_S | 1.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ3_XS.gguf) | IQ3_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ3_M.gguf) | IQ3_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q8_0.gguf) | Q8_0 | 1.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.f16.gguf) | f16 | 3.4 | 16 bpw, overkill | + +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. + +