commit 1c7f2c0ffea61bcb54fc0b940d7648d176b70283 Author: ModelHub XC Date: Mon Jun 1 12:10:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sushi-0.6b-nano-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..883ed21 --- /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 +sushi-0.6b-nano-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sushi-0.6b-nano-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8765995 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: bigatuna/sushi-0.6b-nano-v1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/bigatuna/sushi-0.6b-nano-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#sushi-0.6b-nano-v1-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/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sushi-0.6b-nano-v1-GGUF/resolve/main/sushi-0.6b-nano-v1.f16.gguf) | f16 | 1.3 | 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/sushi-0.6b-nano-v1.IQ4_XS.gguf b/sushi-0.6b-nano-v1.IQ4_XS.gguf new file mode 100644 index 0000000..b260f4b --- /dev/null +++ b/sushi-0.6b-nano-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eca0345bfd038694415aa5ee86cc910bc96673fb4902a038ce547cce3867e64 +size 369278240 diff --git a/sushi-0.6b-nano-v1.Q2_K.gguf b/sushi-0.6b-nano-v1.Q2_K.gguf new file mode 100644 index 0000000..b98d474 --- /dev/null +++ b/sushi-0.6b-nano-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d314c4963835f6b0539b21641d6328faadf713c9d9f9ab33ac681525ae4c51bb +size 296238368 diff --git a/sushi-0.6b-nano-v1.Q3_K_L.gguf b/sushi-0.6b-nano-v1.Q3_K_L.gguf new file mode 100644 index 0000000..6e27f76 --- /dev/null +++ b/sushi-0.6b-nano-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:919fdb621489c7b75dd975fb80055da798cb518dce06ee064373250e99495114 +size 368491808 diff --git a/sushi-0.6b-nano-v1.Q3_K_M.gguf b/sushi-0.6b-nano-v1.Q3_K_M.gguf new file mode 100644 index 0000000..8b95c37 --- /dev/null +++ b/sushi-0.6b-nano-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4084f04c2eeeeaf786724d442b1df1f5c31f6d397ae00851467421d63e0cc6ec +size 347127072 diff --git a/sushi-0.6b-nano-v1.Q3_K_S.gguf b/sushi-0.6b-nano-v1.Q3_K_S.gguf new file mode 100644 index 0000000..f03c664 --- /dev/null +++ b/sushi-0.6b-nano-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8791318f0e27eac360ea58530b6f7da9cb7f606037bd8e3e79f6b8e651f566 +size 323075360 diff --git a/sushi-0.6b-nano-v1.Q4_K_M.gguf b/sushi-0.6b-nano-v1.Q4_K_M.gguf new file mode 100644 index 0000000..2857b7d --- /dev/null +++ b/sushi-0.6b-nano-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfaa2405fed25b5810cab95564333933c049e7a7bf437b9f390bb5d7ec9a410 +size 396705056 diff --git a/sushi-0.6b-nano-v1.Q4_K_S.gguf b/sushi-0.6b-nano-v1.Q4_K_S.gguf new file mode 100644 index 0000000..b91f91a --- /dev/null +++ b/sushi-0.6b-nano-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fbdff8f27931ce467b35521feb410f6a63de4954ddef303708ad2fcaacb6926 +size 383270176 diff --git a/sushi-0.6b-nano-v1.Q5_K_M.gguf b/sushi-0.6b-nano-v1.Q5_K_M.gguf new file mode 100644 index 0000000..69c6c8d --- /dev/null +++ b/sushi-0.6b-nano-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e891562f164771d7db4f221706122fcd989ea0652d01e369b9f90145bb5d716 +size 444415264 diff --git a/sushi-0.6b-nano-v1.Q5_K_S.gguf b/sushi-0.6b-nano-v1.Q5_K_S.gguf new file mode 100644 index 0000000..d945db8 --- /dev/null +++ b/sushi-0.6b-nano-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7887b7b646b26b41711cfc71752fe11aaedf8d0bb5bd10e1f65cd665e9a6300 +size 436616480 diff --git a/sushi-0.6b-nano-v1.Q6_K.gguf b/sushi-0.6b-nano-v1.Q6_K.gguf new file mode 100644 index 0000000..9592725 --- /dev/null +++ b/sushi-0.6b-nano-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373710dde71799267d365034224d89710de38b6f5885c7977e0a6357605ca28b +size 495107360 diff --git a/sushi-0.6b-nano-v1.Q8_0.gguf b/sushi-0.6b-nano-v1.Q8_0.gguf new file mode 100644 index 0000000..858ba74 --- /dev/null +++ b/sushi-0.6b-nano-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8f2f35d58737c64f2401028e13552a88b4f7762fab9bd706af43855833322c +size 639447328 diff --git a/sushi-0.6b-nano-v1.f16.gguf b/sushi-0.6b-nano-v1.f16.gguf new file mode 100644 index 0000000..6e3dd92 --- /dev/null +++ b/sushi-0.6b-nano-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404fc119c06ced435570db70e4b2a30da3a8fcb314038917b26b96431054b9a0 +size 1198182688