commit 5d41513bd5d26f92bf582d1f31f08812a519bca0 Author: ModelHub XC Date: Sat Jun 13 10:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nano-r1-model-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..535eabd --- /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 +nano-r1-model.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nano-r1-model.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c7ee1aa --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Mansi-30/nano-r1-model +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/Mansi-30/nano-r1-model + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#nano-r1-model-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/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nano-r1-model-GGUF/resolve/main/nano-r1-model.f16.gguf) | f16 | 6.3 | 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. + + diff --git a/nano-r1-model.IQ4_XS.gguf b/nano-r1-model.IQ4_XS.gguf new file mode 100644 index 0000000..d575a52 --- /dev/null +++ b/nano-r1-model.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5419df9a53e34d8d30fdf2e8f6b45071f7ec81bf4bf1bc3c482ddd8194f2971e +size 1753185632 diff --git a/nano-r1-model.Q2_K.gguf b/nano-r1-model.Q2_K.gguf new file mode 100644 index 0000000..2f9bacc --- /dev/null +++ b/nano-r1-model.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2a22374c9b0ee70daafe389b363eb8868660ddf86e83e48e72c14399173ebc +size 1274756448 diff --git a/nano-r1-model.Q3_K_L.gguf b/nano-r1-model.Q3_K_L.gguf new file mode 100644 index 0000000..d7dcc3b --- /dev/null +++ b/nano-r1-model.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:693c87d9df40e920c41936d7f8a87c042bbc145cd42b87ade73e80b5e1ffcae1 +size 1707392352 diff --git a/nano-r1-model.Q3_K_M.gguf b/nano-r1-model.Q3_K_M.gguf new file mode 100644 index 0000000..9f0976f --- /dev/null +++ b/nano-r1-model.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b568627e065a8f8aa3b42c2f83d44424da0e180c79d45989beaafcf235993b14 +size 1590476128 diff --git a/nano-r1-model.Q3_K_S.gguf b/nano-r1-model.Q3_K_S.gguf new file mode 100644 index 0000000..0dafd36 --- /dev/null +++ b/nano-r1-model.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf27037d780b4d2f51f3533f1df6af3308fd18b1aa03dfacfc6caf60a38ee52b +size 1454357856 diff --git a/nano-r1-model.Q4_K_M.gguf b/nano-r1-model.Q4_K_M.gguf new file mode 100644 index 0000000..a84e30f --- /dev/null +++ b/nano-r1-model.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481fd05a6e45152a2032773b0ff3173f1ba3df5e88a0b1a2f1719470be2e68de +size 1929903456 diff --git a/nano-r1-model.Q4_K_S.gguf b/nano-r1-model.Q4_K_S.gguf new file mode 100644 index 0000000..f28862b --- /dev/null +++ b/nano-r1-model.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344817b5efff304a470d6c4ce48a4d942100aaff6673458ca46f3e4718aad74d +size 1834384736 diff --git a/nano-r1-model.Q5_K_M.gguf b/nano-r1-model.Q5_K_M.gguf new file mode 100644 index 0000000..b6599c5 --- /dev/null +++ b/nano-r1-model.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91f2ab0a313a444e371a6de330dcb8047d0777dba146e7b03093c9bbf6c6d7d +size 2224815456 diff --git a/nano-r1-model.Q5_K_S.gguf b/nano-r1-model.Q5_K_S.gguf new file mode 100644 index 0000000..06ac8bb --- /dev/null +++ b/nano-r1-model.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a52036d24f7da3c50108281667853d31237fc92346e743237ed3318fff642d53 +size 2169666912 diff --git a/nano-r1-model.Q6_K.gguf b/nano-r1-model.Q6_K.gguf new file mode 100644 index 0000000..4b07fed --- /dev/null +++ b/nano-r1-model.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c26b0434e4abede5e66a86fd3350458e9c9ece250173be2a9fe34e032dc4ed44 +size 2538159456 diff --git a/nano-r1-model.Q8_0.gguf b/nano-r1-model.Q8_0.gguf new file mode 100644 index 0000000..b51e5b0 --- /dev/null +++ b/nano-r1-model.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3b0fd0c6d5ecea20b656fdfaf64df8acb2da644986c6ec8bb03f37d99d5409 +size 3285476704 diff --git a/nano-r1-model.f16.gguf b/nano-r1-model.f16.gguf new file mode 100644 index 0000000..438885c --- /dev/null +++ b/nano-r1-model.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:090344e19f1653bd330ae3134781a7ca758631f3441f1d7ec0e90041248c0fa0 +size 6178317664