commit 73e44457fba21e8fbfd3be4b5bea9225b2d35492 Author: ModelHub XC Date: Tue Apr 14 01:35:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-Nano-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..07e2e05 --- /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-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-Nano-Instruct.IQ4_XS.gguf b/Marco-Nano-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..879d6e9 --- /dev/null +++ b/Marco-Nano-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b0878f27a13bdb749f03e625f39ca574d2089b174cb43578ebd9deb72303a1 +size 4456140320 diff --git a/Marco-Nano-Instruct.Q2_K.gguf b/Marco-Nano-Instruct.Q2_K.gguf new file mode 100644 index 0000000..8ad5768 --- /dev/null +++ b/Marco-Nano-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bcc98962a9a72fbef153f67acc085124752dec39aa04df8f65d89f6a67fc2fb +size 3340291616 diff --git a/Marco-Nano-Instruct.Q3_K_L.gguf b/Marco-Nano-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..a8c36f4 --- /dev/null +++ b/Marco-Nano-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c7d15c4faaed496b48a7e8b2afcdd3b3f6640959e3bf8b0a31194c11ab6104 +size 4369731104 diff --git a/Marco-Nano-Instruct.Q3_K_M.gguf b/Marco-Nano-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..bff31ba --- /dev/null +++ b/Marco-Nano-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94634aa773b1b51ce4d44ad72026163bc2de0eb7985f7fdba86e9d2f53b1bc32 +size 4205039136 diff --git a/Marco-Nano-Instruct.Q3_K_S.gguf b/Marco-Nano-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..89f133c --- /dev/null +++ b/Marco-Nano-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96d4e2a5e2749e8ff144fabc485f84111a4a9e997478f99c66713db9769c343 +size 3868085792 diff --git a/Marco-Nano-Instruct.Q4_K_M.gguf b/Marco-Nano-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..26c9291 --- /dev/null +++ b/Marco-Nano-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e5756e58baf127cd15f1f78d72d3d34c62f445a08aaa28ea37750dc22952b0 +size 5371989536 diff --git a/Marco-Nano-Instruct.Q4_K_S.gguf b/Marco-Nano-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..ae05f24 --- /dev/null +++ b/Marco-Nano-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06dc4301ef52f85d761d43cc8afe5911e5a57a8089fdd67fa9bcee9d2dcfec24 +size 4906896928 diff --git a/Marco-Nano-Instruct.Q5_K_M.gguf b/Marco-Nano-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..ed85b33 --- /dev/null +++ b/Marco-Nano-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c57a08d250239dc2924e2116d912bac1a8f10f6614e7440a3807cbe601f5f92 +size 6110580256 diff --git a/Marco-Nano-Instruct.Q5_K_S.gguf b/Marco-Nano-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..139bb50 --- /dev/null +++ b/Marco-Nano-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe9dc6cffbc9b1b00db6249120b0ecae99a10848b956da01a28c118eac48e687 +size 5709516320 diff --git a/Marco-Nano-Instruct.Q6_K.gguf b/Marco-Nano-Instruct.Q6_K.gguf new file mode 100644 index 0000000..e3f122b --- /dev/null +++ b/Marco-Nano-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5cb09799cc155eb6f5df2ab2a531e48f1d0e9efd3d844587f2c2398d2bf225 +size 7209635360 diff --git a/Marco-Nano-Instruct.Q8_0.gguf b/Marco-Nano-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ebb8ecf --- /dev/null +++ b/Marco-Nano-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d582f96ef67d4b06dcbcb8e28063e8bc2383c1e7d5cecb28e3f8f427a5be3c +size 8527233568 diff --git a/Marco-Nano-Instruct.f16.gguf b/Marco-Nano-Instruct.f16.gguf new file mode 100644 index 0000000..9388a9a --- /dev/null +++ b/Marco-Nano-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4ae629fedbe2861efe5bcbfea9977a8a04c121a4b0b203dd470f635fc496c5 +size 16022299168 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c959615 --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +base_model: AIDC-AI/Marco-Nano-Instruct +datasets: +- allenai/Dolci-Instruct-SFT +- nvidia/Nemotron-Cascade-2-SFT-Data +- nvidia/Nemotron-RL-instruction_following +- nvidia/Nemotron-RL-instruction_following-structured_outputs +- nvidia/Nemotron-RL-ReasoningGym-v1 +- nvidia/Nemotron-RL-knowledge-mcqa +- nvidia/Nemotron-Cascade-RL-RLHF +- BytedTsinghua-SIA/DAPO-Math-17k +- Skywork/Skywork-OR1-RL-Data +- nvidia/Nemotron-SFT-Multilingual-v1 +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/AIDC-AI/Marco-Nano-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-Nano-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Marco-Nano-Instruct-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-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q4_K_S.gguf) | Q4_K_S | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q6_K.gguf) | Q6_K | 7.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-GGUF/resolve/main/Marco-Nano-Instruct.f16.gguf) | f16 | 16.1 | 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. + +