commit 705eef59f1a4ec9885d2f1e343989cf090b99de9 Author: ModelHub XC Date: Wed May 13 10:24:35 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-Mini-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e433e83 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-Mini-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Mini-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-Mini-Instruct.IQ4_XS.gguf b/Marco-Mini-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..2bb9dea --- /dev/null +++ b/Marco-Mini-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e24247650b558364a324ca472f3092b0c76985475a7692f525e61bbcf17f83da +size 9335361088 diff --git a/Marco-Mini-Instruct.Q2_K.gguf b/Marco-Mini-Instruct.Q2_K.gguf new file mode 100644 index 0000000..5e4e477 --- /dev/null +++ b/Marco-Mini-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99ad7f3016497e4abbdfe898082bd9931c9258c67c499e34d719dcdac6acad6 +size 6351539776 diff --git a/Marco-Mini-Instruct.Q3_K_L.gguf b/Marco-Mini-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1f778cc --- /dev/null +++ b/Marco-Mini-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92e8f32a890d837edd4e7efd16e6351ed6d69a43e11e3972b43079d5b563dbf +size 8981564992 diff --git a/Marco-Mini-Instruct.Q3_K_M.gguf b/Marco-Mini-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..33fde80 --- /dev/null +++ b/Marco-Mini-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13364ac3faa23647a6f3fa6beea66b88878fb6164c50929967aa6c98fefeb47 +size 8291339840 diff --git a/Marco-Mini-Instruct.Q3_K_S.gguf b/Marco-Mini-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..cd819a9 --- /dev/null +++ b/Marco-Mini-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b9caaed7142ff680728e0ac484ca6496d6e42a98710299f8a46c9c61c70ee88 +size 7505530432 diff --git a/Marco-Mini-Instruct.Q4_K_M.gguf b/Marco-Mini-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..a903113 --- /dev/null +++ b/Marco-Mini-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a75f5a9bca31c7156cc44b439ecd56192469d770a538d91f342786e2805548ea +size 10505424448 diff --git a/Marco-Mini-Instruct.Q4_K_S.gguf b/Marco-Mini-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..e5d756f --- /dev/null +++ b/Marco-Mini-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc84df08e9e8894d15519bf60a744294ee7b6704e7c6582d7badb47927fc1269 +size 9850998336 diff --git a/Marco-Mini-Instruct.Q5_K_M.gguf b/Marco-Mini-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a87aaf5 --- /dev/null +++ b/Marco-Mini-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3aa76d4e2edae0ca003ee8935766ecf1ffdbb957b462484ce2d70e66ba6afd +size 12287217216 diff --git a/Marco-Mini-Instruct.Q5_K_S.gguf b/Marco-Mini-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..68c39b7 --- /dev/null +++ b/Marco-Mini-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d655d4a95ea3b5b2e2c7b2adaefef7f96d5c4eb17f9a3f26772387606add3dcb +size 11910925888 diff --git a/Marco-Mini-Instruct.Q6_K.gguf b/Marco-Mini-Instruct.Q6_K.gguf new file mode 100644 index 0000000..c27bcf0 --- /dev/null +++ b/Marco-Mini-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14136859ec014db9f23d7a97f6e46023fbda2c16137f0f8d8213f5ded7bfa00 +size 14180372032 diff --git a/Marco-Mini-Instruct.Q8_0.gguf b/Marco-Mini-Instruct.Q8_0.gguf new file mode 100644 index 0000000..77d7930 --- /dev/null +++ b/Marco-Mini-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3287457af7a6632cce7b9e9dd37a7bce72f6e61c3d64eb79deea474bda5e6f1c +size 18356453952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..04b6a73 --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +base_model: AIDC-AI/Marco-Mini-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 +- on-policy distillation +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AIDC-AI/Marco-Mini-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-Mini-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Marco-Mini-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-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q2_K.gguf) | Q2_K | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q3_K_S.gguf) | Q3_K_S | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q3_K_M.gguf) | Q3_K_M | 8.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q3_K_L.gguf) | Q3_K_L | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.IQ4_XS.gguf) | IQ4_XS | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q4_K_S.gguf) | Q4_K_S | 10.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q4_K_M.gguf) | Q4_K_M | 10.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q5_K_S.gguf) | Q5_K_S | 12.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q5_K_M.gguf) | Q5_K_M | 12.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q6_K.gguf) | Q6_K | 14.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Mini-Instruct-GGUF/resolve/main/Marco-Mini-Instruct.Q8_0.gguf) | Q8_0 | 18.5 | fast, best quality | + +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. + +