commit 700364e35a5a6057b34c09d21b342af2527cae7f Author: ModelHub XC Date: Sat Jun 27 01:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RakutenAI-2.0-mini-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a07e7fc --- /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 +RakutenAI-2.0-mini-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-2.0-mini-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5e1fcb5 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: atarayosd/RakutenAI-2.0-mini-instruct +language: +- en +- ja +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mlx +--- +## About + + + + + + +static quants of https://huggingface.co/atarayosd/RakutenAI-2.0-mini-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RakutenAI-2.0-mini-instruct-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/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-2.0-mini-instruct-GGUF/resolve/main/RakutenAI-2.0-mini-instruct.f16.gguf) | f16 | 3.2 | 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/RakutenAI-2.0-mini-instruct.IQ4_XS.gguf b/RakutenAI-2.0-mini-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..d141e50 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b8d9dd83b229b40b1a6d7a7fc16de63ff5010c312dbd9875d86fdd4c999b166 +size 853988832 diff --git a/RakutenAI-2.0-mini-instruct.Q2_K.gguf b/RakutenAI-2.0-mini-instruct.Q2_K.gguf new file mode 100644 index 0000000..f8805e9 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a6fd00ac01818551150d6369b507eb19595fd5f857d9b25b1696e37429a19f +size 605660640 diff --git a/RakutenAI-2.0-mini-instruct.Q3_K_L.gguf b/RakutenAI-2.0-mini-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c4ce8ca --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b03332c318280685d3953a2d455f170b94beef96b0b9c0bab768de86c98d5a9 +size 824163808 diff --git a/RakutenAI-2.0-mini-instruct.Q3_K_M.gguf b/RakutenAI-2.0-mini-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b011bb0 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90054e96263fe2692844189d585724c4f40bab4492e13be5ba5e5a8dd6b13368 +size 765967840 diff --git a/RakutenAI-2.0-mini-instruct.Q3_K_S.gguf b/RakutenAI-2.0-mini-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..893c341 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50bae700f2880a1d18ccc3818744d723c6e1aaffb64476c5e3e184fff31ceaa2 +size 699268576 diff --git a/RakutenAI-2.0-mini-instruct.Q4_K_M.gguf b/RakutenAI-2.0-mini-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..fd1582e --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9258119534c14b5551b89b01cab16cd8adac574c6d722fedc20b6dc59014e7cd +size 935982560 diff --git a/RakutenAI-2.0-mini-instruct.Q4_K_S.gguf b/RakutenAI-2.0-mini-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..62d2c05 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b17460274631b64e6f91d16ec9b2418e220116c4d71290345fa7cbc6d34261 +size 894744032 diff --git a/RakutenAI-2.0-mini-instruct.Q5_K_M.gguf b/RakutenAI-2.0-mini-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..1cc0d37 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fadaa2d3e9fc77b14e7a6e9b61e6543dc69831e7e7ef5c8906146dc5b5477b4d +size 1093236192 diff --git a/RakutenAI-2.0-mini-instruct.Q5_K_S.gguf b/RakutenAI-2.0-mini-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..931ea94 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e04f2d57d5cbe96932110d9cda38fd433e492ca93b655edaff8df3c751885c +size 1069561312 diff --git a/RakutenAI-2.0-mini-instruct.Q6_K.gguf b/RakutenAI-2.0-mini-instruct.Q6_K.gguf new file mode 100644 index 0000000..2b0cfdb --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f311c352259cdf867d1a79dafabaa78301cd08bdafdade5970ff424b3d8eefb +size 1260318176 diff --git a/RakutenAI-2.0-mini-instruct.Q8_0.gguf b/RakutenAI-2.0-mini-instruct.Q8_0.gguf new file mode 100644 index 0000000..2b25469 --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aedf10c8436e79fdcff58fbf2ba95e9f2178bfdafef39f7f25d351e00ab0d7c4 +size 1631976928 diff --git a/RakutenAI-2.0-mini-instruct.f16.gguf b/RakutenAI-2.0-mini-instruct.f16.gguf new file mode 100644 index 0000000..921013f --- /dev/null +++ b/RakutenAI-2.0-mini-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce0947b7e249712471030179403270c3724256dbbd79a8a0dcfa5086572f32d +size 3070655968