commit 996d696a215d2b991fe92d3ba26f2134ee22391d Author: ModelHub XC Date: Sun Apr 12 13:52:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RakutenAI-7B-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a7ae037 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-7B-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RakutenAI-7B-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3a7e55 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Rakuten/RakutenAI-7B-instruct +language: +- en +- ja +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Rakuten/RakutenAI-7B-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/RakutenAI-7B-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/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q2_K.gguf) | Q2_K | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.IQ3_XS.gguf) | IQ3_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.IQ3_M.gguf) | IQ3_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q3_K_M.gguf) | Q3_K_M | 3.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q3_K_L.gguf) | Q3_K_L | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q5_K_S.gguf) | Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q5_K_M.gguf) | Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q6_K.gguf) | Q6_K | 6.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RakutenAI-7B-instruct-GGUF/resolve/main/RakutenAI-7B-instruct.f16.gguf) | f16 | 14.8 | 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-7B-instruct.IQ3_M.gguf b/RakutenAI-7B-instruct.IQ3_M.gguf new file mode 100644 index 0000000..515d145 --- /dev/null +++ b/RakutenAI-7B-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97220bdfb939e77f502cf0bc0991c1a53a7688913387eba309a89697b9efe180 +size 3367185920 diff --git a/RakutenAI-7B-instruct.IQ3_S.gguf b/RakutenAI-7B-instruct.IQ3_S.gguf new file mode 100644 index 0000000..8043e6a --- /dev/null +++ b/RakutenAI-7B-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:654c0ff3e17ab003da92cb6cf287f6851e2528fe3e4b8874867b5d76713a0b9f +size 3264687616 diff --git a/RakutenAI-7B-instruct.IQ3_XS.gguf b/RakutenAI-7B-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..f1acc02 --- /dev/null +++ b/RakutenAI-7B-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0f1839b6f9f7cebc86f2c185d7734d7d35a2bc0c4c8e4bf23b3ca5320c61e7 +size 3101109760 diff --git a/RakutenAI-7B-instruct.IQ4_XS.gguf b/RakutenAI-7B-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..6743a6a --- /dev/null +++ b/RakutenAI-7B-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05e75c74cce586317db2bf0d565c707d08f7a4e3c89b7d5c10a0f1898b6e0fb +size 4033338880 diff --git a/RakutenAI-7B-instruct.Q2_K.gguf b/RakutenAI-7B-instruct.Q2_K.gguf new file mode 100644 index 0000000..a683333 --- /dev/null +++ b/RakutenAI-7B-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a989c03d8a192155e28319be12660ddf939435acb79ec09626aa0733344d46b +size 2794880512 diff --git a/RakutenAI-7B-instruct.Q3_K_L.gguf b/RakutenAI-7B-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9002258 --- /dev/null +++ b/RakutenAI-7B-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4ffad991c8494cb9a152aac53b92909af5a0f212ca0d558219adcaba0b3a24 +size 3904318976 diff --git a/RakutenAI-7B-instruct.Q3_K_M.gguf b/RakutenAI-7B-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..12fad7e --- /dev/null +++ b/RakutenAI-7B-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4606c34d1c56d9d1db9887e7ff55fcf12455e66c5d1cc2b8272ff1e5446c85d8 +size 3601280512 diff --git a/RakutenAI-7B-instruct.Q3_K_S.gguf b/RakutenAI-7B-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..f242c33 --- /dev/null +++ b/RakutenAI-7B-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d734d96240913b7cdc968012c9afe4bff724d5bf933ad3041759edfddf789538 +size 3246861824 diff --git a/RakutenAI-7B-instruct.Q4_K_M.gguf b/RakutenAI-7B-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c338444 --- /dev/null +++ b/RakutenAI-7B-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eaef718247c31d8b5f40a5f08cacb23b8334e6485909f922b699dde41a18193 +size 4459437568 diff --git a/RakutenAI-7B-instruct.Q4_K_S.gguf b/RakutenAI-7B-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..17f3f52 --- /dev/null +++ b/RakutenAI-7B-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f36fa2278b67a5770849a0741949de08e0bafd3be4ca8705dd74237a113be6 +size 4231372288 diff --git a/RakutenAI-7B-instruct.Q5_K_M.gguf b/RakutenAI-7B-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..d5d65c8 --- /dev/null +++ b/RakutenAI-7B-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09afa773ab2bb835de7762d25589c257800a587774a3aa178a691ec0f8204421 +size 5230599680 diff --git a/RakutenAI-7B-instruct.Q5_K_S.gguf b/RakutenAI-7B-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..c2dacae --- /dev/null +++ b/RakutenAI-7B-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8c5e0ca9e83dc08874915995e0fedcaa98b636b5a9e39d5bba8877731fdaea +size 5096906240 diff --git a/RakutenAI-7B-instruct.Q6_K.gguf b/RakutenAI-7B-instruct.Q6_K.gguf new file mode 100644 index 0000000..9714c7e --- /dev/null +++ b/RakutenAI-7B-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0af5f992d7c34cf0a6aa840741bd82436d337d98cbaa03d9e01c92e39d04e8c +size 6049959424 diff --git a/RakutenAI-7B-instruct.Q8_0.gguf b/RakutenAI-7B-instruct.Q8_0.gguf new file mode 100644 index 0000000..e047c2f --- /dev/null +++ b/RakutenAI-7B-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168d86a4f7625e4c37fe51bb23a447e06572660b8fce89ef8cae3391cd54a8a3 +size 7835495936 diff --git a/RakutenAI-7B-instruct.f16.gguf b/RakutenAI-7B-instruct.f16.gguf new file mode 100644 index 0000000..b6ba612 --- /dev/null +++ b/RakutenAI-7B-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7097aba421fd7f1a9b23280377d78818448050fa29df160ce2a245a373cc0d8b +size 14747250176