commit 8d5d98eda18466c3a25843adeeb19f54cfc0c359 Author: ModelHub XC Date: Sat Apr 11 05:11:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aira-2-124M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b2dd98 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-124M.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aira-2-124M.IQ4_XS.gguf b/Aira-2-124M.IQ4_XS.gguf new file mode 100644 index 0000000..2852ec1 --- /dev/null +++ b/Aira-2-124M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd2dea8d135dd072841ee0e909c5c9b22844ab95b43aa8dccc1324a660ba7ed +size 103068608 diff --git a/Aira-2-124M.Q2_K.gguf b/Aira-2-124M.Q2_K.gguf new file mode 100644 index 0000000..90671eb --- /dev/null +++ b/Aira-2-124M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8cc79d0b2c3edfbea37df41d7e6b799a7e2141666bdb47b82a45060ef244cc2 +size 81201152 diff --git a/Aira-2-124M.Q3_K_L.gguf b/Aira-2-124M.Q3_K_L.gguf new file mode 100644 index 0000000..eb824ac --- /dev/null +++ b/Aira-2-124M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de17133e9a674c3072785eeac0fb03f094b9263fe34b7c1c3771806599ba1c3 +size 102097376 diff --git a/Aira-2-124M.Q3_K_M.gguf b/Aira-2-124M.Q3_K_M.gguf new file mode 100644 index 0000000..f2ceec2 --- /dev/null +++ b/Aira-2-124M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:090be469bfd03f29e0016c7dd87553f95bff513ddd9b99aede51fb8d3c201354 +size 97673696 diff --git a/Aira-2-124M.Q3_K_S.gguf b/Aira-2-124M.Q3_K_S.gguf new file mode 100644 index 0000000..d26cec6 --- /dev/null +++ b/Aira-2-124M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33b71f4a7a1cccba53b963b508c7b00db174147d46fa7160122df51336e64e85 +size 90153440 diff --git a/Aira-2-124M.Q4_K_M.gguf b/Aira-2-124M.Q4_K_M.gguf new file mode 100644 index 0000000..9d6f317 --- /dev/null +++ b/Aira-2-124M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:391761a0c7ca503f15a5ad40401a7d73a7790173f9e4214b342ab9f6a77a4f84 +size 112864192 diff --git a/Aira-2-124M.Q4_K_S.gguf b/Aira-2-124M.Q4_K_S.gguf new file mode 100644 index 0000000..75406e9 --- /dev/null +++ b/Aira-2-124M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e1d6962c1226696f3b6a1bb3661199e8727e473ace7ccf6460c2066bf0d335 +size 106855360 diff --git a/Aira-2-124M.Q5_K_M.gguf b/Aira-2-124M.Q5_K_M.gguf new file mode 100644 index 0000000..5d88c68 --- /dev/null +++ b/Aira-2-124M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac9d4565038651f74dcea800ac490e8864e10c8fe0a8fa45011b8f0dd13bd9c +size 126702496 diff --git a/Aira-2-124M.Q5_K_S.gguf b/Aira-2-124M.Q5_K_S.gguf new file mode 100644 index 0000000..434c8fb --- /dev/null +++ b/Aira-2-124M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50beab6edf300f2643f71fbf036de29f6e4133d749214d289d272919e4f98a8a +size 122002336 diff --git a/Aira-2-124M.Q6_K.gguf b/Aira-2-124M.Q6_K.gguf new file mode 100644 index 0000000..34ec0fd --- /dev/null +++ b/Aira-2-124M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d951bc639d6b32a46f6db97472bdf9dff248764e9f624beababbb00deb57eefa +size 138409344 diff --git a/Aira-2-124M.Q8_0.gguf b/Aira-2-124M.Q8_0.gguf new file mode 100644 index 0000000..cfade41 --- /dev/null +++ b/Aira-2-124M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e228e0cee5ca3ea82f30a998ea354a8587ed6e4d573329f443691c6d98268800 +size 177676544 diff --git a/Aira-2-124M.f16.gguf b/Aira-2-124M.f16.gguf new file mode 100644 index 0000000..a156423 --- /dev/null +++ b/Aira-2-124M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a2a08abc3966062acb0e4facb418009761289d9e40760d0054dff2288b6b1e +size 329678592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0deb419 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +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 + + + + + + +static quants of https://huggingface.co/nicholasKluge/Aira-2-124M + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Aira-2-124M-i1-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-GGUF/resolve/main/Aira-2-124M.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-124M-GGUF/resolve/main/Aira-2-124M.f16.gguf) | f16 | 0.4 | 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. 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. + +