commit 1ab1d62d8f6d30343d4fd903ebed13873f6db5cb Author: ModelHub XC Date: Fri Jun 12 13:40:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/arete-Qwen2.5-3B_1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e763c3c --- /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 +arete-Qwen2.5-3B_1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +arete-Qwen2.5-3B_1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b0b9c6 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Koskath/arete-Qwen2.5-3B_1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Koskath/arete-Qwen2.5-3B_1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#arete-Qwen2.5-3B_1-GGUF).*** + +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/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/arete-Qwen2.5-3B_1-GGUF/resolve/main/arete-Qwen2.5-3B_1.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. + + diff --git a/arete-Qwen2.5-3B_1.IQ4_XS.gguf b/arete-Qwen2.5-3B_1.IQ4_XS.gguf new file mode 100644 index 0000000..91073c7 --- /dev/null +++ b/arete-Qwen2.5-3B_1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e2e6fa86006a02f5abd3b54a6a04da356182703ab0a7910fa1b8aa14c4cb5cf +size 1753185184 diff --git a/arete-Qwen2.5-3B_1.Q2_K.gguf b/arete-Qwen2.5-3B_1.Q2_K.gguf new file mode 100644 index 0000000..652e2f5 --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2cfd148f81aea4f53f0f5b91a4bd9883032c98e372c31d17e6552becce9382c +size 1274756000 diff --git a/arete-Qwen2.5-3B_1.Q3_K_L.gguf b/arete-Qwen2.5-3B_1.Q3_K_L.gguf new file mode 100644 index 0000000..1a8a145 --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51dcc2b8a4824d80159fe31c78ea7fd0b1d5e7765c6346eefe4aca6ea3bedb4c +size 1707391904 diff --git a/arete-Qwen2.5-3B_1.Q3_K_M.gguf b/arete-Qwen2.5-3B_1.Q3_K_M.gguf new file mode 100644 index 0000000..0976bdf --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce565068bac255ee987263435fadea5cddffebd30656ba440be9644bcfb1e7e +size 1590475680 diff --git a/arete-Qwen2.5-3B_1.Q3_K_S.gguf b/arete-Qwen2.5-3B_1.Q3_K_S.gguf new file mode 100644 index 0000000..33158f0 --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0d4d791be77af9b674be042b59bcb95ea6879d3e4d4a570ef879a229eb9689 +size 1454357408 diff --git a/arete-Qwen2.5-3B_1.Q4_K_M.gguf b/arete-Qwen2.5-3B_1.Q4_K_M.gguf new file mode 100644 index 0000000..8421e2c --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ec4da260c878b7872da36af502da60f3dd34b6054634aef7c39135f78ab6073 +size 1929903008 diff --git a/arete-Qwen2.5-3B_1.Q4_K_S.gguf b/arete-Qwen2.5-3B_1.Q4_K_S.gguf new file mode 100644 index 0000000..3269baa --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f3e03f764a5dba883c12788ca031fd56e56ffa82f9069622210932f88f71ad +size 1834384288 diff --git a/arete-Qwen2.5-3B_1.Q5_K_M.gguf b/arete-Qwen2.5-3B_1.Q5_K_M.gguf new file mode 100644 index 0000000..00efba9 --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5df9203428c03dff41349f67d3fe41088ea0482136a6af697289b62e2963cb9 +size 2224815008 diff --git a/arete-Qwen2.5-3B_1.Q5_K_S.gguf b/arete-Qwen2.5-3B_1.Q5_K_S.gguf new file mode 100644 index 0000000..13a7ae4 --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9571bcd914eace3bfb33011861be5a6e7b198ee5d779eb6e50e8c9c2d21a432 +size 2169666464 diff --git a/arete-Qwen2.5-3B_1.Q6_K.gguf b/arete-Qwen2.5-3B_1.Q6_K.gguf new file mode 100644 index 0000000..235c0bf --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c51d0d5189c889d7dafd00cb000208bf5329c04c99e393be83ba77cd1bcc44f +size 2538159008 diff --git a/arete-Qwen2.5-3B_1.Q8_0.gguf b/arete-Qwen2.5-3B_1.Q8_0.gguf new file mode 100644 index 0000000..b2c37d4 --- /dev/null +++ b/arete-Qwen2.5-3B_1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15f96d153ac6dd3e117a60e842c1fb711d590046080e38c22ec81157411eec84 +size 3285476256 diff --git a/arete-Qwen2.5-3B_1.f16.gguf b/arete-Qwen2.5-3B_1.f16.gguf new file mode 100644 index 0000000..969f119 --- /dev/null +++ b/arete-Qwen2.5-3B_1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e7a3e7312667e7332b0f64d171f85dbf53d2fbbac57cef2d67ee5f53b56e8b +size 6178317216