commit 1930d3afbc8cbef2b659db903cabca59d46c0783 Author: ModelHub XC Date: Mon Jun 1 13:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Atomight-0.5b-UltraMath-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d804a9d --- /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 +Atomight-0.5b-UltraMath.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-0.5b-UltraMath.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Atomight-0.5b-UltraMath.IQ4_XS.gguf b/Atomight-0.5b-UltraMath.IQ4_XS.gguf new file mode 100644 index 0000000..a0dbbf1 --- /dev/null +++ b/Atomight-0.5b-UltraMath.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86fd499c37001d392492e9aca7d252d899647bb4c81be3afb9ce0f917df63d7b +size 351445792 diff --git a/Atomight-0.5b-UltraMath.Q2_K.gguf b/Atomight-0.5b-UltraMath.Q2_K.gguf new file mode 100644 index 0000000..aed6dee --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4397ce2ce38eb0f1f7c9026aee2c56e4e12526b0124ed13302514d94bb7363 +size 338607904 diff --git a/Atomight-0.5b-UltraMath.Q3_K_L.gguf b/Atomight-0.5b-UltraMath.Q3_K_L.gguf new file mode 100644 index 0000000..0f7db16 --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf0fd916c519d9a419fe22c1b2b78d3ba85d13da61bf01cd93f1621be7a47054 +size 369358624 diff --git a/Atomight-0.5b-UltraMath.Q3_K_M.gguf b/Atomight-0.5b-UltraMath.Q3_K_M.gguf new file mode 100644 index 0000000..b7e3770 --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36f5b91492930eed6ec2a171d1588de30ba653e0c0040bc2d06d5ad8778bdc9 +size 355467040 diff --git a/Atomight-0.5b-UltraMath.Q3_K_S.gguf b/Atomight-0.5b-UltraMath.Q3_K_S.gguf new file mode 100644 index 0000000..0114b46 --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a31578be7d0b277fcea234ce685139d3f028c746681bd9abe1501767c159f0 +size 338263840 diff --git a/Atomight-0.5b-UltraMath.Q4_K_M.gguf b/Atomight-0.5b-UltraMath.Q4_K_M.gguf new file mode 100644 index 0000000..d81f45a --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602d0f76a921ac97884de41216c302d6095d46365a1ba8d676c85c861bc21a86 +size 397808416 diff --git a/Atomight-0.5b-UltraMath.Q4_K_S.gguf b/Atomight-0.5b-UltraMath.Q4_K_S.gguf new file mode 100644 index 0000000..bc3957d --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4b4f912d12fa40256c57f53d2d463c8dff0f246f6271ab38a40560a89b99d9 +size 385472288 diff --git a/Atomight-0.5b-UltraMath.Q5_K_M.gguf b/Atomight-0.5b-UltraMath.Q5_K_M.gguf new file mode 100644 index 0000000..867ab0d --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6952b0ada68cbd51a6b581ca46cf6780cfd8e0f568091f2ab876563e5e968bd +size 420086560 diff --git a/Atomight-0.5b-UltraMath.Q5_K_S.gguf b/Atomight-0.5b-UltraMath.Q5_K_S.gguf new file mode 100644 index 0000000..a9f6661 --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4703c18e73e7849c44fe4ddd1365d088cb3f96dd56540f9de8c4c5f9b8a0d2 +size 412710688 diff --git a/Atomight-0.5b-UltraMath.Q6_K.gguf b/Atomight-0.5b-UltraMath.Q6_K.gguf new file mode 100644 index 0000000..a87ab71 --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:415cbd3ffd406003c0e0f5589d9a0e5d24539d46011f4cbfb4b043955c2c28fd +size 505736992 diff --git a/Atomight-0.5b-UltraMath.Q8_0.gguf b/Atomight-0.5b-UltraMath.Q8_0.gguf new file mode 100644 index 0000000..fde47b4 --- /dev/null +++ b/Atomight-0.5b-UltraMath.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea6ce91ed4430e57e2a6be191d43b9322ad2d3e9ee0a58217ad9a23e71f228f +size 531068704 diff --git a/Atomight-0.5b-UltraMath.f16.gguf b/Atomight-0.5b-UltraMath.f16.gguf new file mode 100644 index 0000000..f689ab4 --- /dev/null +++ b/Atomight-0.5b-UltraMath.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5759a21555b14c14e4daebdc1d2400aa13bb1518da9ab1c3a39d5296f554244 +size 994157344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..db36120 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: NovatasticRoScript/Atomight-0.5b-UltraMath +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/NovatasticRoScript/Atomight-0.5b-UltraMath + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Atomight-0.5b-UltraMath-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/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Atomight-0.5b-UltraMath-GGUF/resolve/main/Atomight-0.5b-UltraMath.f16.gguf) | f16 | 1.1 | 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. + +