commit 684c7d70689a45ca7b2319f4f0238dc7cea2785e Author: ModelHub XC Date: Tue May 5 07:42:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aira-2-1B1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..27d15cd --- /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-2-1B1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aira-2-1B1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aira-2-1B1.IQ4_XS.gguf b/Aira-2-1B1.IQ4_XS.gguf new file mode 100644 index 0000000..25cf633 --- /dev/null +++ b/Aira-2-1B1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b249bc3a44b5762bd4d261e6b6617032ec1847d636721c7ad2551e3a24c7a6d5 +size 609822240 diff --git a/Aira-2-1B1.Q2_K.gguf b/Aira-2-1B1.Q2_K.gguf new file mode 100644 index 0000000..781c460 --- /dev/null +++ b/Aira-2-1B1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6dadb8fce250e381a9779fcbbf9ad66f4cf5d032811f3d4a4055bb848ddcece +size 432143872 diff --git a/Aira-2-1B1.Q3_K_L.gguf b/Aira-2-1B1.Q3_K_L.gguf new file mode 100644 index 0000000..6c377ca --- /dev/null +++ b/Aira-2-1B1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a8dc49a1fb77f4038b68ba32ea1587560e0e7d3f3b0e99e893246b21fb8dc5 +size 591540768 diff --git a/Aira-2-1B1.Q3_K_M.gguf b/Aira-2-1B1.Q3_K_M.gguf new file mode 100644 index 0000000..244222c --- /dev/null +++ b/Aira-2-1B1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d8ea9f6ea3f7f5a9b620d5f6fab9bc35109462faa77aaa0336b8bd36709a6c +size 548418080 diff --git a/Aira-2-1B1.Q3_K_S.gguf b/Aira-2-1B1.Q3_K_S.gguf new file mode 100644 index 0000000..7731e2b --- /dev/null +++ b/Aira-2-1B1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8daee315823ade6bdf4060626bb399e56e3e8941197b84377d0b308e3837b1ce +size 499356192 diff --git a/Aira-2-1B1.Q4_K_M.gguf b/Aira-2-1B1.Q4_K_M.gguf new file mode 100644 index 0000000..4fd92e7 --- /dev/null +++ b/Aira-2-1B1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb51f0ed27ffc136b31a623b7a7d12b2b49971e6ccc9f75f450c083782bbc4c +size 667830112 diff --git a/Aira-2-1B1.Q4_K_S.gguf b/Aira-2-1B1.Q4_K_S.gguf new file mode 100644 index 0000000..b3053b6 --- /dev/null +++ b/Aira-2-1B1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d44722776fbc4144ed50aa55b18f24229e445569d3f9184359c85ec46253bc +size 639887200 diff --git a/Aira-2-1B1.Q5_K_M.gguf b/Aira-2-1B1.Q5_K_M.gguf new file mode 100644 index 0000000..ef69dca --- /dev/null +++ b/Aira-2-1B1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db4c997c7fff88911957c8c8ad8b81466835aa70b3ee57b1df2dd2ab494736cc +size 782060640 diff --git a/Aira-2-1B1.Q5_K_S.gguf b/Aira-2-1B1.Q5_K_S.gguf new file mode 100644 index 0000000..4641df9 --- /dev/null +++ b/Aira-2-1B1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd0d364f92eca0b28958fb5aec8b246ffe7f0482ca034a7dc877aa1b85db331 +size 766045280 diff --git a/Aira-2-1B1.Q6_K.gguf b/Aira-2-1B1.Q6_K.gguf new file mode 100644 index 0000000..6a3216e --- /dev/null +++ b/Aira-2-1B1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c501fa4cdbd916f8eda5445450341a916fe574f1192b33625285ba67e958281a +size 903430592 diff --git a/Aira-2-1B1.Q8_0.gguf b/Aira-2-1B1.Q8_0.gguf new file mode 100644 index 0000000..edaaeb9 --- /dev/null +++ b/Aira-2-1B1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f94c37c56f5cb0dfea274fc082c3339088c234174ed7bd316b48073f674a1c +size 1169831168 diff --git a/Aira-2-1B1.f16.gguf b/Aira-2-1B1.f16.gguf new file mode 100644 index 0000000..2bde2d0 --- /dev/null +++ b/Aira-2-1B1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2745c98d88d192c6d3ef2e45601176e2820b5875e2b91f2a5208137acd937af8 +size 2201059328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f7248e2 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: nicholasKluge/Aira-2-1B1 +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-2-1B1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Aira-2-1B1-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-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B1-GGUF/resolve/main/Aira-2-1B1.f16.gguf) | f16 | 2.3 | 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. + +