commit ac07b362dba9c7f937a4305beebc43a57b3d2c5a Author: ModelHub XC Date: Fri Jul 10 02:24:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7d8c98c --- /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 +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.f16.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NVIDIA-Nemotron-Nano-9B-v2-Japanese.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.IQ4_XS.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.IQ4_XS.gguf new file mode 100644 index 0000000..284dde2 --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce60039b2d14109c6ecbfe2e48f9f704462b7dfb28e559477ccc3eeffb81c48 +size 5359306880 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q2_K.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q2_K.gguf new file mode 100644 index 0000000..ca0d5a0 --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f12abf1da6de37a98c24cae18c82ed34d078f4ec5e7e7a5a8bce934e22cd45 +size 5006193280 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_L.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_L.gguf new file mode 100644 index 0000000..898df8f --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb977392b34c2fae71706ec30b2bbf521136e8e0d57844ddb5217ff88745f44 +size 5488366720 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_M.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_M.gguf new file mode 100644 index 0000000..c35aa1d --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e734a435ea01e01d3af43831a4dc4f1550e3a0d06f0725fa00c513c49580a115 +size 5379735680 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_S.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_S.gguf new file mode 100644 index 0000000..eba133a --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f351e7911b51da168af1b4069b58be5e635bc83b4afb79d91b96d4c17e400e55 +size 5131991680 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_M.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_M.gguf new file mode 100644 index 0000000..b06b02d --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea3ade1a406efb755566b7e5713166b1a425fb005225446586baf7e1cbaef86 +size 6525630080 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_S.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_S.gguf new file mode 100644 index 0000000..772651c --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e58202d205fdd1c23d03d79a85ef5b9ee8954ad21a87303fb1eddcf404c67b3 +size 6211617920 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_M.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_M.gguf new file mode 100644 index 0000000..5f90f13 --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb8212c405e321b7dced65ea8f7090d57f6bd793b1d95057e32f091bd04b75a +size 7069806720 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_S.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_S.gguf new file mode 100644 index 0000000..9dc399a --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9373ff0e8b20dbf3faf81d607679ce1f4627d13c131960b4c6e177e3fe117b0 +size 6781563520 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q6_K.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q6_K.gguf new file mode 100644 index 0000000..73aa89e --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bccc6067ca3b8b1c9880b5ba34290d03b5578b7974972624fcaa6c7f7e06fec +size 9135893120 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q8_0.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q8_0.gguf new file mode 100644 index 0000000..efd182f --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82739379f3a7c45383e292a7a593f8fbe786a10065569f3bbe3ef661ca98bfb1 +size 9458094720 diff --git a/NVIDIA-Nemotron-Nano-9B-v2-Japanese.f16.gguf b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.f16.gguf new file mode 100644 index 0000000..69d7ae5 --- /dev/null +++ b/NVIDIA-Nemotron-Nano-9B-v2-Japanese.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06d4ec5bd5d084d99aef4e855653becb5e5360a880493cbe529116873aa8921 +size 17788744320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..524bd66 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: urufura/NVIDIA-Nemotron-Nano-9B-v2-Japanese +datasets: +- nvidia/Nemotron-Personas-Japan +- nvidia/Nemotron-CC-v2.1 +- nvidia/Nemotron-Pretraining-Specialized-v1 +- nvidia/Nemotron-Agentic-v1 +- nvidia/Nemotron-Instruction-Following-Chat-v1 +- globis-university/aozorabunko-clean +- HuggingFaceFW/fineweb-2 +language: +- en +- ja +library_name: transformers +license: other +license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/ +license_name: nvidia-nemotron-open-model-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nvidia +- pytorch +--- +## About + + + + + + + + + +static quants of https://huggingface.co/urufura/NVIDIA-Nemotron-Nano-9B-v2-Japanese + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-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/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q2_K.gguf) | Q2_K | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_S.gguf) | Q3_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.IQ4_XS.gguf) | IQ4_XS | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_M.gguf) | Q3_K_M | 5.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q3_K_L.gguf) | Q3_K_L | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_S.gguf) | Q4_K_S | 6.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_S.gguf) | Q5_K_S | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q5_K_M.gguf) | Q5_K_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q6_K.gguf) | Q6_K | 9.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.Q8_0.gguf) | Q8_0 | 9.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-GGUF/resolve/main/NVIDIA-Nemotron-Nano-9B-v2-Japanese.f16.gguf) | f16 | 17.9 | 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. + +