commit 46d1912126a57837688078d40c57415971ed51ef Author: ModelHub XC Date: Fri Oct 16 06:58:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NinjaV1-pre-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c0aa487 --- /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 +NinjaV1-pre.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.f16.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NinjaV1-pre.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NinjaV1-pre.IQ4_XS.gguf b/NinjaV1-pre.IQ4_XS.gguf new file mode 100644 index 0000000..66ee92e --- /dev/null +++ b/NinjaV1-pre.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617017ece55e7e67ff05eda8836f08168f91b83a60a5f9d66199aed3c20f53f3 +size 3944389216 diff --git a/NinjaV1-pre.Q2_K.gguf b/NinjaV1-pre.Q2_K.gguf new file mode 100644 index 0000000..3839da8 --- /dev/null +++ b/NinjaV1-pre.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:171c9a788d35301c00c4181d1baf0e18b0806704004395c6cd1f1979523b0cf5 +size 2719242848 diff --git a/NinjaV1-pre.Q3_K_L.gguf b/NinjaV1-pre.Q3_K_L.gguf new file mode 100644 index 0000000..642c3a8 --- /dev/null +++ b/NinjaV1-pre.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe07ddf085c8d19e93893ffca9b7ce983f01dd384fbce36172d49c919f2a963 +size 3822025312 diff --git a/NinjaV1-pre.Q3_K_M.gguf b/NinjaV1-pre.Q3_K_M.gguf new file mode 100644 index 0000000..9cdd736 --- /dev/null +++ b/NinjaV1-pre.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ee3dc488701c959f08d03160aada2580be2c632fdc94aa617a39f8cb1462e5 +size 3518986848 diff --git a/NinjaV1-pre.Q3_K_S.gguf b/NinjaV1-pre.Q3_K_S.gguf new file mode 100644 index 0000000..615fc97 --- /dev/null +++ b/NinjaV1-pre.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce76a88c64f05bf43c354bd9541fca288239bafcc6d7be4e2d5927091e0d73e +size 3164568160 diff --git a/NinjaV1-pre.Q4_K_M.gguf b/NinjaV1-pre.Q4_K_M.gguf new file mode 100644 index 0000000..7721045 --- /dev/null +++ b/NinjaV1-pre.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cae4e05583b8bc53eaf74afb21dd54c0ddbb1886999678961f2b34978a6d1623 +size 4368439904 diff --git a/NinjaV1-pre.Q4_K_S.gguf b/NinjaV1-pre.Q4_K_S.gguf new file mode 100644 index 0000000..52ae815 --- /dev/null +++ b/NinjaV1-pre.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2b6c7b96d9d53c5759257bd037a8fbccfb35d36a24405a59d80998549cdcf1 +size 4140374624 diff --git a/NinjaV1-pre.Q5_K_M.gguf b/NinjaV1-pre.Q5_K_M.gguf new file mode 100644 index 0000000..64f1d25 --- /dev/null +++ b/NinjaV1-pre.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3b0e81f962fc9157d1f1e1d6fd05a3d16a08887b6dba5de2eb5726108098bb +size 5131410016 diff --git a/NinjaV1-pre.Q5_K_S.gguf b/NinjaV1-pre.Q5_K_S.gguf new file mode 100644 index 0000000..c7924b0 --- /dev/null +++ b/NinjaV1-pre.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c6d0aaef99de8f189b6a93365881692c98317cd8628b55485f4b72c84d3f79e +size 4997716576 diff --git a/NinjaV1-pre.Q6_K.gguf b/NinjaV1-pre.Q6_K.gguf new file mode 100644 index 0000000..123a2b4 --- /dev/null +++ b/NinjaV1-pre.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9db6921af2e6ac6fafd60e08e5ddc0382b66ad3cd27b3a7f2b221f5fd8cd9b +size 5942065760 diff --git a/NinjaV1-pre.Q8_0.gguf b/NinjaV1-pre.Q8_0.gguf new file mode 100644 index 0000000..bc21b51 --- /dev/null +++ b/NinjaV1-pre.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9532a877846e41a57b09eca1afb8650d8affe4e25ef1f5f1a67689f8d05bf5b1 +size 7695858272 diff --git a/NinjaV1-pre.f16.gguf b/NinjaV1-pre.f16.gguf new file mode 100644 index 0000000..8c6a89f --- /dev/null +++ b/NinjaV1-pre.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a7254e9eabeb609fb240c69423c72de7c3285be5594562b14257bbf0bf7874 +size 14484732512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8fc7462 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: umisetokikaze/NinjaV1-pre +language: +- ja +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- LLM +--- +## About + + + + + + +static quants of https://huggingface.co/umisetokikaze/NinjaV1-pre + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NinjaV1-pre-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/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NinjaV1-pre-GGUF/resolve/main/NinjaV1-pre.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. + +