commit d59d82a1e3ed343fbdfbf0ddc5e0c6e110a62407 Author: ModelHub XC Date: Mon Jun 1 20:33:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aya-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47e6139 --- /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 +Aya-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aya-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aya-3B.IQ4_XS.gguf b/Aya-3B.IQ4_XS.gguf new file mode 100644 index 0000000..4ec7d61 --- /dev/null +++ b/Aya-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb75c526fc7824ee58a7768b91533d121877c76d1cbcbac983b59cbf3368cbe +size 1753182880 diff --git a/Aya-3B.Q2_K.gguf b/Aya-3B.Q2_K.gguf new file mode 100644 index 0000000..e567e73 --- /dev/null +++ b/Aya-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1337a8480682e7dfdfaa4ea25fea8b8b6cf8d53c48a66da57620a5fe4f31abb2 +size 1274753696 diff --git a/Aya-3B.Q3_K_L.gguf b/Aya-3B.Q3_K_L.gguf new file mode 100644 index 0000000..88f8659 --- /dev/null +++ b/Aya-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c6134588497ba9d610619176f2f4f5a021d3b17d2c3a50ef6cb9f1568171f2 +size 1707389600 diff --git a/Aya-3B.Q3_K_M.gguf b/Aya-3B.Q3_K_M.gguf new file mode 100644 index 0000000..ecefe4e --- /dev/null +++ b/Aya-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f803b078fe2fbf1b652a8173e8e8810a1abe11231476ea9ed1a229daba3e854 +size 1590473376 diff --git a/Aya-3B.Q3_K_S.gguf b/Aya-3B.Q3_K_S.gguf new file mode 100644 index 0000000..dff3fd5 --- /dev/null +++ b/Aya-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71100279230e0bec67fd9694f1224264ed32efce194fe092cfbd2dc4d904eac9 +size 1454355104 diff --git a/Aya-3B.Q4_K_M.gguf b/Aya-3B.Q4_K_M.gguf new file mode 100644 index 0000000..ac7d53c --- /dev/null +++ b/Aya-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02f1fd4831941c39ee8e44a32b8c99c501de062d73455258f7fa7d371089822 +size 1929900704 diff --git a/Aya-3B.Q4_K_S.gguf b/Aya-3B.Q4_K_S.gguf new file mode 100644 index 0000000..b08f38d --- /dev/null +++ b/Aya-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ab15f5b058d282a97d81ad3f29e3cd6b8ba25fe591fa1fbdcadc4f50a050cb +size 1834381984 diff --git a/Aya-3B.Q5_K_M.gguf b/Aya-3B.Q5_K_M.gguf new file mode 100644 index 0000000..b745159 --- /dev/null +++ b/Aya-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd5ace3e6556040a02b59175ede3327d6fa437db9fccb075f6fb83c883fe438 +size 2224812704 diff --git a/Aya-3B.Q5_K_S.gguf b/Aya-3B.Q5_K_S.gguf new file mode 100644 index 0000000..272b85e --- /dev/null +++ b/Aya-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa0996e12d9dff1e02ac31a01c230deef80f1c482fe61e6a2d768a5012831990 +size 2169664160 diff --git a/Aya-3B.Q6_K.gguf b/Aya-3B.Q6_K.gguf new file mode 100644 index 0000000..b2ea395 --- /dev/null +++ b/Aya-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4276ea4d6e30ef50529b483b79c057e11a6e94ac2a4d32117d2a93278c302028 +size 2538156704 diff --git a/Aya-3B.Q8_0.gguf b/Aya-3B.Q8_0.gguf new file mode 100644 index 0000000..57a9691 --- /dev/null +++ b/Aya-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5375af95d9290c038923371a86cecb5a847f1479eaf6ba3890d55772c416d229 +size 3285473952 diff --git a/Aya-3B.f16.gguf b/Aya-3B.f16.gguf new file mode 100644 index 0000000..0baf463 --- /dev/null +++ b/Aya-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e1c42af71149b2d080a18c044fdb2ba7204e8671f147ea5fc5770bbb633c45 +size 6178314912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..033ebe6 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: sujalrajpoot/Aya-3B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/sujalrajpoot/Aya-3B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Aya-3B-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/Aya-3B-GGUF/resolve/main/Aya-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aya-3B-GGUF/resolve/main/Aya-3B.f16.gguf) | f16 | 6.3 | 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. + +