commit 1011bf39b3f01f5543613048611e2b4d6336c581 Author: ModelHub XC Date: Tue May 26 08:35:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Koto-Small-7b-rc1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..732f2b9 --- /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 +Koto-Small-7b-rc1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Koto-Small-7b-rc1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Koto-Small-7b-rc1.IQ4_XS.gguf b/Koto-Small-7b-rc1.IQ4_XS.gguf new file mode 100644 index 0000000..ce18f9b --- /dev/null +++ b/Koto-Small-7b-rc1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d999f80d339cd78590fc08b060bc6cc99cbeb6fd9f928e440e68596105039692 +size 4288634336 diff --git a/Koto-Small-7b-rc1.Q2_K.gguf b/Koto-Small-7b-rc1.Q2_K.gguf new file mode 100644 index 0000000..3c2335b --- /dev/null +++ b/Koto-Small-7b-rc1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52eea18e1dd3037042b887f8e4f553022f477de238333f9e304cea828735ccf9 +size 3076406752 diff --git a/Koto-Small-7b-rc1.Q3_K_L.gguf b/Koto-Small-7b-rc1.Q3_K_L.gguf new file mode 100644 index 0000000..fe43ba6 --- /dev/null +++ b/Koto-Small-7b-rc1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a34e7b4cca2e7206b780111baeb45981c0dc24c7a50b4afa24c59e076021ca +size 4138962400 diff --git a/Koto-Small-7b-rc1.Q3_K_M.gguf b/Koto-Small-7b-rc1.Q3_K_M.gguf new file mode 100644 index 0000000..8cdd465 --- /dev/null +++ b/Koto-Small-7b-rc1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb3b3997e16ae844a7168735b0d092dad209673e37cdcdc98ed27ee25cec259 +size 3854011872 diff --git a/Koto-Small-7b-rc1.Q3_K_S.gguf b/Koto-Small-7b-rc1.Q3_K_S.gguf new file mode 100644 index 0000000..15546fe --- /dev/null +++ b/Koto-Small-7b-rc1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9c81bfda4e998cbbfb3af73c0dca55ba069f22d6db8d234dfc440425828f87 +size 3525840352 diff --git a/Koto-Small-7b-rc1.Q4_K_M.gguf b/Koto-Small-7b-rc1.Q4_K_M.gguf new file mode 100644 index 0000000..0d0797f --- /dev/null +++ b/Koto-Small-7b-rc1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b02c6b315567e9546bc07f7491b3de29cfbabd3533bc4e255c7210624065b60 +size 4684340704 diff --git a/Koto-Small-7b-rc1.Q4_K_S.gguf b/Koto-Small-7b-rc1.Q4_K_S.gguf new file mode 100644 index 0000000..9763027 --- /dev/null +++ b/Koto-Small-7b-rc1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2794664989c04a6bc27107444e1399630f4d4d96a932006f015fa8ca53f3a56a +size 4480277984 diff --git a/Koto-Small-7b-rc1.Q5_K_M.gguf b/Koto-Small-7b-rc1.Q5_K_M.gguf new file mode 100644 index 0000000..71e7a68 --- /dev/null +++ b/Koto-Small-7b-rc1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38328baedda42e26fea0c961d31390683ddc58d678c887349497a38d3d6ef215 +size 5448556000 diff --git a/Koto-Small-7b-rc1.Q5_K_S.gguf b/Koto-Small-7b-rc1.Q5_K_S.gguf new file mode 100644 index 0000000..a6b71b5 --- /dev/null +++ b/Koto-Small-7b-rc1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c3c25c3d0a02e775ca6fa60dfbbea777e0dc7a29315bc121149ee8aa6ca4d64 +size 5330738656 diff --git a/Koto-Small-7b-rc1.Q6_K.gguf b/Koto-Small-7b-rc1.Q6_K.gguf new file mode 100644 index 0000000..8283d41 --- /dev/null +++ b/Koto-Small-7b-rc1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44cb73736124be3a07f26cd96e59efbf920d512efb2dab3b9a97d7e5399c21ae +size 6260534752 diff --git a/Koto-Small-7b-rc1.Q8_0.gguf b/Koto-Small-7b-rc1.Q8_0.gguf new file mode 100644 index 0000000..2f1e8dd --- /dev/null +++ b/Koto-Small-7b-rc1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe881666cee4aa03bcc4d704f6c1c6aaa5e79397c9585d9232f0c67db396400e +size 8106511840 diff --git a/Koto-Small-7b-rc1.f16.gguf b/Koto-Small-7b-rc1.f16.gguf new file mode 100644 index 0000000..907d130 --- /dev/null +++ b/Koto-Small-7b-rc1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01e8d4a09fd8552e9d18716f235d6e5cf81d63cd978a1b2950dbd868437a109 +size 15252229600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..efc862a --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: allura-org/Koto-Small-7B-PT +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- writing +- creative-writing +--- +## About + + + + + + + + + +static quants of https://huggingface.co/allura-org/Koto-Small-7B-PT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Koto-Small-7b-rc1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Koto-Small-7b-rc1-i1-GGUF +## 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/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Koto-Small-7b-rc1-GGUF/resolve/main/Koto-Small-7b-rc1.f16.gguf) | f16 | 15.4 | 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. + +