commit e6a74345c4b4ad73d2a5ed5f0ca247ea86864b80 Author: ModelHub XC Date: Wed May 13 21:07:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/kural-mistral-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a57268 --- /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 +kural-mistral-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kural-mistral-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d206056 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: shibi76/kural-mistral-7b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +--- +## About + + + + + + + + + +static quants of https://huggingface.co/shibi76/kural-mistral-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#kural-mistral-7b-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/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/kural-mistral-7b-GGUF/resolve/main/kural-mistral-7b.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. + + diff --git a/kural-mistral-7b.IQ4_XS.gguf b/kural-mistral-7b.IQ4_XS.gguf new file mode 100644 index 0000000..793ef6d --- /dev/null +++ b/kural-mistral-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee34db39eebdd77e42146840560d0f1d035977ef848fe425dcf2b5e58fda27d +size 3948667552 diff --git a/kural-mistral-7b.Q2_K.gguf b/kural-mistral-7b.Q2_K.gguf new file mode 100644 index 0000000..e3227eb --- /dev/null +++ b/kural-mistral-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3312e1eafea9fe9741f1c65f5ef15d941079931f8aaf4996871dc68ebb4ebf +size 2722882208 diff --git a/kural-mistral-7b.Q3_K_L.gguf b/kural-mistral-7b.Q3_K_L.gguf new file mode 100644 index 0000000..8fdcbba --- /dev/null +++ b/kural-mistral-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8184fa6212db230d29fc3667f8792d3c25fa36a267313b60ff1139589e2b6917 +size 3825984160 diff --git a/kural-mistral-7b.Q3_K_M.gguf b/kural-mistral-7b.Q3_K_M.gguf new file mode 100644 index 0000000..5b58cb0 --- /dev/null +++ b/kural-mistral-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f87c46646e97d1bd371093d27828c7f79915b26316275c99ce52fbec9205698 +size 3522945696 diff --git a/kural-mistral-7b.Q3_K_S.gguf b/kural-mistral-7b.Q3_K_S.gguf new file mode 100644 index 0000000..7dac7d4 --- /dev/null +++ b/kural-mistral-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e04a0cae77195818142a3fa0052247fdb7f82415e072b8c71ce422b7ededf8 +size 3168527008 diff --git a/kural-mistral-7b.Q4_K_M.gguf b/kural-mistral-7b.Q4_K_M.gguf new file mode 100644 index 0000000..3fbe7c2 --- /dev/null +++ b/kural-mistral-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd5d825fb9d26fc0b368c763b8736663d0028512baf172e40e9c338012bebc1 +size 4372816544 diff --git a/kural-mistral-7b.Q4_K_S.gguf b/kural-mistral-7b.Q4_K_S.gguf new file mode 100644 index 0000000..c784e4d --- /dev/null +++ b/kural-mistral-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e895e11ad2206e1fdfd888dcaba36c1ec6b9d1e31d4ccf260a1bcf7ed846fe10 +size 4144751264 diff --git a/kural-mistral-7b.Q5_K_M.gguf b/kural-mistral-7b.Q5_K_M.gguf new file mode 100644 index 0000000..3c76257 --- /dev/null +++ b/kural-mistral-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caef040b216293a05f4e6f92002e253355345f5c0a67660feff11049335471cf +size 5136179872 diff --git a/kural-mistral-7b.Q5_K_S.gguf b/kural-mistral-7b.Q5_K_S.gguf new file mode 100644 index 0000000..d498e90 --- /dev/null +++ b/kural-mistral-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:589b30516daf57460546719ba2205039e504457c346f2a9814164e4096499e8b +size 5002486432 diff --git a/kural-mistral-7b.Q6_K.gguf b/kural-mistral-7b.Q6_K.gguf new file mode 100644 index 0000000..571423c --- /dev/null +++ b/kural-mistral-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c132248e5b866d27c3153af16d711a46662a7ae4ce150f40de2b3430d0e5509 +size 5947253408 diff --git a/kural-mistral-7b.Q8_0.gguf b/kural-mistral-7b.Q8_0.gguf new file mode 100644 index 0000000..d6b9384 --- /dev/null +++ b/kural-mistral-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be5784ed40bbc5580dbc76ab837c010f538d0d50df9b8f9951ce30a7946c4b30 +size 7702569632 diff --git a/kural-mistral-7b.f16.gguf b/kural-mistral-7b.f16.gguf new file mode 100644 index 0000000..941e274 --- /dev/null +++ b/kural-mistral-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e6e811f3075ef193363e80723bb267318d6120359226908a0f755fc825d5a79 +size 14497342112