commit 82fa38411495b731ba589ecea68600c85cdb32b9 Author: ModelHub XC Date: Mon Aug 10 19:52:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-Nano-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d29ac68 --- /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 +Marco-Nano-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-Nano-Base.IQ4_XS.gguf b/Marco-Nano-Base.IQ4_XS.gguf new file mode 100644 index 0000000..b518541 --- /dev/null +++ b/Marco-Nano-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc21c725c3fb70c9cdb4fed0fb363bc5b7f8418a40475f24e7ff881d71441464 +size 4538794336 diff --git a/Marco-Nano-Base.Q2_K.gguf b/Marco-Nano-Base.Q2_K.gguf new file mode 100644 index 0000000..e6ddf09 --- /dev/null +++ b/Marco-Nano-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9571f14c5f75674f56502c7846c3237df66de123eee7aae751c14be5ad2153aa +size 3391342944 diff --git a/Marco-Nano-Base.Q3_K_L.gguf b/Marco-Nano-Base.Q3_K_L.gguf new file mode 100644 index 0000000..68da21c --- /dev/null +++ b/Marco-Nano-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5413e8a85c9523c662ca7ff5ae9f44c0a9a5f0b2e1e1881e3816dff5d6750e41 +size 4436583776 diff --git a/Marco-Nano-Base.Q3_K_M.gguf b/Marco-Nano-Base.Q3_K_M.gguf new file mode 100644 index 0000000..748f5c8 --- /dev/null +++ b/Marco-Nano-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21dc4b5cc95fee28875ad2ac0ae6466d3884a35aa5a4ad88a4c778e7db631f70 +size 4271891808 diff --git a/Marco-Nano-Base.Q3_K_S.gguf b/Marco-Nano-Base.Q3_K_S.gguf new file mode 100644 index 0000000..227d677 --- /dev/null +++ b/Marco-Nano-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e035c6ab038a8dca2309f0c8dee2e6fa596353d48c2158b368075d53d3dc3450 +size 3934938464 diff --git a/Marco-Nano-Base.Q4_K_M.gguf b/Marco-Nano-Base.Q4_K_M.gguf new file mode 100644 index 0000000..8aa0254 --- /dev/null +++ b/Marco-Nano-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc4654da967328b079166f5ef518782bfa5c001c78ecedcdff0541879734b89 +size 5459505504 diff --git a/Marco-Nano-Base.Q4_K_S.gguf b/Marco-Nano-Base.Q4_K_S.gguf new file mode 100644 index 0000000..5095968 --- /dev/null +++ b/Marco-Nano-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aad08d7303fd7733b28078063f83046573cab964ae10736f3b5ce90b1d9aa07f +size 4994412896 diff --git a/Marco-Nano-Base.Q5_K_M.gguf b/Marco-Nano-Base.Q5_K_M.gguf new file mode 100644 index 0000000..e8f97eb --- /dev/null +++ b/Marco-Nano-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208133e518191fc9c87979198a8455291dbcf2ff3fefde39ed0540a0900e5f2f +size 6217544032 diff --git a/Marco-Nano-Base.Q5_K_S.gguf b/Marco-Nano-Base.Q5_K_S.gguf new file mode 100644 index 0000000..6009c05 --- /dev/null +++ b/Marco-Nano-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8936dddd1ff360de8728fcb5210e3f7c14b150ffea5b0621fe97c3d93f3e4d +size 5816480096 diff --git a/Marco-Nano-Base.Q6_K.gguf b/Marco-Nano-Base.Q6_K.gguf new file mode 100644 index 0000000..de400bc --- /dev/null +++ b/Marco-Nano-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5b2822ca498b5247ab6bbaa3291070355b9b07afea09f43d228645d65fc65a +size 7337262432 diff --git a/Marco-Nano-Base.Q8_0.gguf b/Marco-Nano-Base.Q8_0.gguf new file mode 100644 index 0000000..d71b4de --- /dev/null +++ b/Marco-Nano-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:953e232cc5032e5d6b19caebd1bc4c49af7557c4a34023645c169bb61d05ee78 +size 8692540768 diff --git a/Marco-Nano-Base.f16.gguf b/Marco-Nano-Base.f16.gguf new file mode 100644 index 0000000..b80dad2 --- /dev/null +++ b/Marco-Nano-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69fad9176027850feae1d0731163337f05c62f6a8d4dbaddaa00983c919c0b5c +size 16333464928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3d22a90 --- /dev/null +++ b/README.md @@ -0,0 +1,119 @@ +--- +base_model: ATH-MaaS/Marco-Nano-Base +datasets: +- nvidia/Nemotron-CC-v2 +- nvidia/Nemotron-Pretraining-SFT-v1 +- nvidia/Nemotron-Pretraining-Specialized-v1 +- nvidia/Nemotron-CC-v2.1 +- allenai/dolmino-mix-1124 +- nvidia/Nemotron-CC-Math-v1 +- nvidia/OpenMathInstruct-2 +- HuggingFaceTB/finemath +- LLM360/MegaMath +- open-thoughts/OpenThoughts3-1.2M +- opencsg/Fineweb-Edu-Chinese-V2.1 +- HuggingFaceFW/fineweb-2 +- allenai/dolma3_dolmino_mix-100B-1125 +language: +- en +- zh +- ar +- de +- es +- fr +- ko +- ja +- pt +- tr +- id +- it +- nl +- pl +- ru +- vi +- th +- he +- uk +- ms +- bn +- cs +- ur +- kk +- el +- ro +- hu +- ne +- az +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- moe +- mixture-of-experts +- multilingual +- upcycling +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ATH-MaaS/Marco-Nano-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-Nano-Base-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Marco-Nano-Base-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/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q4_K_M.gguf) | Q4_K_M | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q5_K_S.gguf) | Q5_K_S | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q5_K_M.gguf) | Q5_K_M | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q6_K.gguf) | Q6_K | 7.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.f16.gguf) | f16 | 16.4 | 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. + +