commit 6d79e73c400c80c85cbe8743f23d224df9e24b3f Author: ModelHub XC Date: Wed Sep 9 02:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e92813 --- /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 +Mistral7BInstructv0.2-RakutenAI7Bchat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral7BInstructv0.2-RakutenAI7Bchat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.IQ4_XS.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.IQ4_XS.gguf new file mode 100644 index 0000000..816e3ec --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c49ee0d3dd449ed6cf08eee755f2a88102eea5add3861e81e0dbd570e6b47a3 +size 3944390272 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q2_K.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q2_K.gguf new file mode 100644 index 0000000..ee0c459 --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3524f0a63ba7fe86a4dd67c9145c88a7f9eaf3aa3e885185aa7ea269c9e738 +size 2719243904 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_L.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_L.gguf new file mode 100644 index 0000000..ffeb465 --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7920319164b8276a0df95866231495149ddcd6c28b47f6cd37ad5966a1337a66 +size 3822026368 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_M.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_M.gguf new file mode 100644 index 0000000..9f62fbe --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da0cc3ff09e013d56648f1c9134537b412a02087599ce746286c768b4f438a7 +size 3518987904 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_S.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_S.gguf new file mode 100644 index 0000000..28b6b04 --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0256848f9bf5ea32d68d24e079a0036c27cc10a7bb5d56eb8a83bea8ac42c592 +size 3164569216 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_M.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_M.gguf new file mode 100644 index 0000000..4f94a55 --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b1afefed020e0db2b2e0e12c8e1ea8f7933a9362fea51214f3b6a7822cad4f7 +size 4368440960 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_S.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_S.gguf new file mode 100644 index 0000000..08316e1 --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f31a94a4a2f13b4465803562f0ca28ce4c9b48d88ef7503c1d1adfebfbef8e +size 4140375680 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_M.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_M.gguf new file mode 100644 index 0000000..6eeb2d6 --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6693f0d004f5601ff855e0339138d3490cbfe294e56a707340eaee799f0ad41d +size 5131411072 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_S.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_S.gguf new file mode 100644 index 0000000..859f54c --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c4f35b94b32c281602a41a5975a381cad9e934d8d3b10c8613e8760b0ca080 +size 4997717632 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q6_K.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q6_K.gguf new file mode 100644 index 0000000..94c87b6 --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11075876a901a2fad651950143b3592874eb85662816a6a3b9210c9b474205b9 +size 5942066816 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.Q8_0.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q8_0.gguf new file mode 100644 index 0000000..b9320ba --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:467823392cc48bc08a734a121475f6698d6be2c99a9fdba0d179afdd13b8130f +size 7695859328 diff --git a/Mistral7BInstructv0.2-RakutenAI7Bchat.f16.gguf b/Mistral7BInstructv0.2-RakutenAI7Bchat.f16.gguf new file mode 100644 index 0000000..5aaf6ed --- /dev/null +++ b/Mistral7BInstructv0.2-RakutenAI7Bchat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f30c8a7ca2bdaa9d3207e22cc582c1d4fd5994acbfed9fc3bdddb4b203cf3d +size 14484733568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2682e8d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: iemon-kun/Mistral7BInstructv0.2-RakutenAI7Bchat +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/iemon-kun/Mistral7BInstructv0.2-RakutenAI7Bchat + + +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/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral7BInstructv0.2-RakutenAI7Bchat-GGUF/resolve/main/Mistral7BInstructv0.2-RakutenAI7Bchat.f16.gguf) | f16 | 14.6 | 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. + +