commit 018d3de724fcdf795a1f269f55d406590617454a Author: ModelHub XC Date: Sun Jun 21 20:34:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/karasu-1.1B-linear2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9eb940e --- /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 +karasu-1.1B-linear2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +karasu-1.1B-linear2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..41b0a86 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: aipib/karasu-1.1B-linear2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- lightblue/karasu-1.1B +- niryuu/Karasu-1.1b-chat-vector +--- +## About + + + + + + +static quants of https://huggingface.co/aipib/karasu-1.1B-linear2 + + +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/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/karasu-1.1B-linear2-GGUF/resolve/main/karasu-1.1B-linear2.f16.gguf) | f16 | 2.3 | 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/karasu-1.1B-linear2.IQ4_XS.gguf b/karasu-1.1B-linear2.IQ4_XS.gguf new file mode 100644 index 0000000..392b5ee --- /dev/null +++ b/karasu-1.1B-linear2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22fe20217c795597f3dd295f4bfe037d759b7f3d3afd35bcb77cbf373f7a3a8c +size 609808800 diff --git a/karasu-1.1B-linear2.Q2_K.gguf b/karasu-1.1B-linear2.Q2_K.gguf new file mode 100644 index 0000000..8612b8a --- /dev/null +++ b/karasu-1.1B-linear2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e45febd11b1be743c165c45191892b1c7ba28fe6ade6312eda98bf73c4d09d8a +size 432132512 diff --git a/karasu-1.1B-linear2.Q3_K_L.gguf b/karasu-1.1B-linear2.Q3_K_L.gguf new file mode 100644 index 0000000..c034456 --- /dev/null +++ b/karasu-1.1B-linear2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2109b5b07d24d05ff8894c71091500d401403528845d6acd76ccf0d502065ec +size 591528352 diff --git a/karasu-1.1B-linear2.Q3_K_M.gguf b/karasu-1.1B-linear2.Q3_K_M.gguf new file mode 100644 index 0000000..9271764 --- /dev/null +++ b/karasu-1.1B-linear2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e8b01517e60f331d9cd3df911883607b8f40acc8790466398b22b11f2d404d +size 548405664 diff --git a/karasu-1.1B-linear2.Q3_K_S.gguf b/karasu-1.1B-linear2.Q3_K_S.gguf new file mode 100644 index 0000000..5e61999 --- /dev/null +++ b/karasu-1.1B-linear2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b91ed0fd582d247869a85d5f80d38e2f644a5deea4f4b230c58a12f0cde908d +size 499343776 diff --git a/karasu-1.1B-linear2.Q4_K_M.gguf b/karasu-1.1B-linear2.Q4_K_M.gguf new file mode 100644 index 0000000..28ec234 --- /dev/null +++ b/karasu-1.1B-linear2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d9b72575c8f1e8bff8756645d1e472a20014453668334ed0c81b916019a112 +size 667816352 diff --git a/karasu-1.1B-linear2.Q4_K_S.gguf b/karasu-1.1B-linear2.Q4_K_S.gguf new file mode 100644 index 0000000..a67769e --- /dev/null +++ b/karasu-1.1B-linear2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6f9e38f13370ec6b0c5c280524d313ff2eec9c2d7b8ef98835938d6f59eeac +size 639873440 diff --git a/karasu-1.1B-linear2.Q5_K_M.gguf b/karasu-1.1B-linear2.Q5_K_M.gguf new file mode 100644 index 0000000..65ea4da --- /dev/null +++ b/karasu-1.1B-linear2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212c4ee027ea31e457ccdd1c6db0f2df0e33c4cbac4c54e180b599ff94bcd7e8 +size 782045600 diff --git a/karasu-1.1B-linear2.Q5_K_S.gguf b/karasu-1.1B-linear2.Q5_K_S.gguf new file mode 100644 index 0000000..10da3c8 --- /dev/null +++ b/karasu-1.1B-linear2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82bd018b18cefbe08958900b1a12247a7b690ca06f3afdcd3921849c5f3ad83b +size 766030240 diff --git a/karasu-1.1B-linear2.Q6_K.gguf b/karasu-1.1B-linear2.Q6_K.gguf new file mode 100644 index 0000000..c67350b --- /dev/null +++ b/karasu-1.1B-linear2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112cb44e8f85296a34d7dde20379c86596a28fb568668f97513f3a23565d8503 +size 903414176 diff --git a/karasu-1.1B-linear2.Q8_0.gguf b/karasu-1.1B-linear2.Q8_0.gguf new file mode 100644 index 0000000..2d08968 --- /dev/null +++ b/karasu-1.1B-linear2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9197d963799f5acc10c554613228dfdabad7ce9b72d7dea5be424efbe0035498 +size 1169809824 diff --git a/karasu-1.1B-linear2.f16.gguf b/karasu-1.1B-linear2.f16.gguf new file mode 100644 index 0000000..8eb7cba --- /dev/null +++ b/karasu-1.1B-linear2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d96028b37036df74344791ff2e9b01bede3d2793988acba12bf4f4d481e3b059 +size 2201018784