commit 01f8724ecb39602d84d9cd7f5c31a330004c42b4 Author: ModelHub XC Date: Sun May 24 01:28:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenMath-Nemotron-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d4d00b9 --- /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 +OpenMath-Nemotron-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenMath-Nemotron-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenMath-Nemotron-1.5B.IQ4_XS.gguf b/OpenMath-Nemotron-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..1412007 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a93a5317e320c27e34fd2f74590f94c1063361e876a7d96d1613847bde834f1 +size 902181536 diff --git a/OpenMath-Nemotron-1.5B.Q2_K.gguf b/OpenMath-Nemotron-1.5B.Q2_K.gguf new file mode 100644 index 0000000..66dea05 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3bb76e15478fba5c357570cd8549cd5a4ac217f4a889d818f7143e65e9eb91 +size 676303520 diff --git a/OpenMath-Nemotron-1.5B.Q3_K_L.gguf b/OpenMath-Nemotron-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..33981fd --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e135b232b5a06278103684495cc0a4f9c165ea58e39bae35a6f533f69a848c17 +size 880161440 diff --git a/OpenMath-Nemotron-1.5B.Q3_K_M.gguf b/OpenMath-Nemotron-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..9157e42 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1d06815220f98613d838e3f05b57f45713a9d175838b8a02b276654c79486a +size 824177312 diff --git a/OpenMath-Nemotron-1.5B.Q3_K_S.gguf b/OpenMath-Nemotron-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..4269afc --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb65a9238d91e83b8f578719d08a70d393dc94cf5848bed44dab83d204993522 +size 760943264 diff --git a/OpenMath-Nemotron-1.5B.Q4_K_M.gguf b/OpenMath-Nemotron-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..5c79f8c --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f64190222d009ab9a30e0bda88c568d2b20cbc8e1a4eda941258f364d0d53a +size 986047136 diff --git a/OpenMath-Nemotron-1.5B.Q4_K_S.gguf b/OpenMath-Nemotron-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..7f41888 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec10dd06dda5165b8051df23891927ceb83836eab3d6cbacaea27d3ff407865 +size 940311200 diff --git a/OpenMath-Nemotron-1.5B.Q5_K_M.gguf b/OpenMath-Nemotron-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..75d9116 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9704f19ee497136f73162d2e2d6f3b243d17684ea68409419b332d9c2927daa +size 1125048992 diff --git a/OpenMath-Nemotron-1.5B.Q5_K_S.gguf b/OpenMath-Nemotron-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..5f1ffe5 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63655e08247e9c6ebc4d2de504924824cac937100fa57350402361d19bdc1412 +size 1098728096 diff --git a/OpenMath-Nemotron-1.5B.Q6_K.gguf b/OpenMath-Nemotron-1.5B.Q6_K.gguf new file mode 100644 index 0000000..79aef73 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682f2252eb67089d33db569368dc7dade4d5426f5e484995f7a4cc9b943bb67d +size 1272738464 diff --git a/OpenMath-Nemotron-1.5B.Q8_0.gguf b/OpenMath-Nemotron-1.5B.Q8_0.gguf new file mode 100644 index 0000000..3abe79a --- /dev/null +++ b/OpenMath-Nemotron-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26ab430891839e874f61bbf931cfbb2976d7bf051b7159d3e840b555928a84d +size 1646571680 diff --git a/OpenMath-Nemotron-1.5B.f16.gguf b/OpenMath-Nemotron-1.5B.f16.gguf new file mode 100644 index 0000000..2110b75 --- /dev/null +++ b/OpenMath-Nemotron-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac176dc13b0def43753568118fcb2064a85b31d834eda11e975272cbedb962a +size 3093668000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b07f74e --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: nvidia/OpenMath-Nemotron-1.5B +datasets: +- nvidia/OpenMathReasoning +language: +- en +library_name: transformers +license: cc-by-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nvidia +- math +--- +## About + + + + + + +static quants of https://huggingface.co/nvidia/OpenMath-Nemotron-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OpenMath-Nemotron-1.5B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-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/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenMath-Nemotron-1.5B-GGUF/resolve/main/OpenMath-Nemotron-1.5B.f16.gguf) | f16 | 3.2 | 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. + +