commit f23f97d8d4751175b4b4db80282f3c2b1b422a40 Author: ModelHub XC Date: Thu Jun 25 15:42:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KawaiiMahou-llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c31f049 --- /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 +KawaiiMahou-llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KawaiiMahou-llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KawaiiMahou-llama3-8B.IQ3_M.gguf b/KawaiiMahou-llama3-8B.IQ3_M.gguf new file mode 100644 index 0000000..dfba039 --- /dev/null +++ b/KawaiiMahou-llama3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf7155d4cd0a88611b4dac2f139f3af3a4fc9feae7b58b6f8d4d5c9c29c932c +size 3784823488 diff --git a/KawaiiMahou-llama3-8B.IQ3_S.gguf b/KawaiiMahou-llama3-8B.IQ3_S.gguf new file mode 100644 index 0000000..805c7f1 --- /dev/null +++ b/KawaiiMahou-llama3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fccab64267f296b09639bb075f1a57695d14f3b36ed4b40ecd66b47c6e7107f +size 3682325184 diff --git a/KawaiiMahou-llama3-8B.IQ3_XS.gguf b/KawaiiMahou-llama3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..bc63e29 --- /dev/null +++ b/KawaiiMahou-llama3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19adfe9cd8c997d50867ff21155ae14a33116271db7340db9d189ecacbf0a134 +size 3518747328 diff --git a/KawaiiMahou-llama3-8B.IQ4_XS.gguf b/KawaiiMahou-llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..eddac00 --- /dev/null +++ b/KawaiiMahou-llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a1a1412768c104abea683900dc5a17c3dd327890e24773be48c207b9b223b8 +size 4484362944 diff --git a/KawaiiMahou-llama3-8B.Q2_K.gguf b/KawaiiMahou-llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..52ed8aa --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25fc417a7602cc8cac5085620e919d9e267497339a734fda8dd0c90780641cfe +size 3179131584 diff --git a/KawaiiMahou-llama3-8B.Q3_K_L.gguf b/KawaiiMahou-llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..401e46a --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a08f582f7349e38c014b4079445f91770fc1f97bb0ac9a8a6ecbd8917f9e2d +size 4321956544 diff --git a/KawaiiMahou-llama3-8B.Q3_K_M.gguf b/KawaiiMahou-llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..3253ea5 --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9bf8dcf51a0b52f47183831400e4ee27b2e7c632c61fa32aed52ce104731afa +size 4018918080 diff --git a/KawaiiMahou-llama3-8B.Q3_K_S.gguf b/KawaiiMahou-llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..38f508e --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84b6af33aa7270a0e5f0a77f89bd8f8a3414ce4e623d0b342f4d402d9a06ad6 +size 3664499392 diff --git a/KawaiiMahou-llama3-8B.Q4_K_M.gguf b/KawaiiMahou-llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..bf400ea --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf7a6d5bc3f05a9ea8e741e08ca1fdc5ec2a370251a899bd96cee0987a57b20 +size 4920734400 diff --git a/KawaiiMahou-llama3-8B.Q4_K_S.gguf b/KawaiiMahou-llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..8f0b053 --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d5c504602d3bf242d7a2aa42398e105cf894028834ba42a7c85deec34fad05 +size 4692669120 diff --git a/KawaiiMahou-llama3-8B.Q5_K_M.gguf b/KawaiiMahou-llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..632e492 --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58cedefddea6648397811fec380aaa9617b3e568c6b1d6296fae0e05b58c07c5 +size 5732987584 diff --git a/KawaiiMahou-llama3-8B.Q5_K_S.gguf b/KawaiiMahou-llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..d7bbcca --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5bae5b86852f8d0f393f311838adaa72279e6a2a471bc415b5a47334b0c0dc +size 5599294144 diff --git a/KawaiiMahou-llama3-8B.Q6_K.gguf b/KawaiiMahou-llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..1f55cec --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c6bfc35197a8d3125177d9470cd1b426a0673d0c0f8ff5d2faee94cd37e22fb +size 6596006592 diff --git a/KawaiiMahou-llama3-8B.Q8_0.gguf b/KawaiiMahou-llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..bb9fbbe --- /dev/null +++ b/KawaiiMahou-llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b678f51169286d8e2d71ff1bc2b939d2fc2608d624efec73f54c7b29734fe0b8 +size 8540771008 diff --git a/KawaiiMahou-llama3-8B.f16.gguf b/KawaiiMahou-llama3-8B.f16.gguf new file mode 100644 index 0000000..9bb56c7 --- /dev/null +++ b/KawaiiMahou-llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e92dc414444d84d4cfdcff35b6a891ec118f78e7d0b7dae7b7aecbc00b366a +size 16068891328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..224f8b9 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: nbeerbower/KawaiiMahou-llama3-8B +datasets: +- yongtae-jp/orca_dpo_pairs_ja +language: +- en +library_name: transformers +license: other +license_name: llama3 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + +static quants of https://huggingface.co/nbeerbower/KawaiiMahou-llama3-8B + + +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/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KawaiiMahou-llama3-8B-GGUF/resolve/main/KawaiiMahou-llama3-8B.f16.gguf) | f16 | 16.2 | 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. + +