commit e3f428fb3e89f1d01b82adc0781a4092e7043cbf Author: ModelHub XC Date: Thu Jun 11 09:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KAI-7B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..70699d5 --- /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 +KAI-7B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KAI-7B-v0.1.IQ3_M.gguf b/KAI-7B-v0.1.IQ3_M.gguf new file mode 100644 index 0000000..536e003 --- /dev/null +++ b/KAI-7B-v0.1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b711cd783e41fcead6e65342790b6f960fc1a88f633406724ab60570fcd76068 +size 3284892352 diff --git a/KAI-7B-v0.1.IQ3_S.gguf b/KAI-7B-v0.1.IQ3_S.gguf new file mode 100644 index 0000000..ba77e89 --- /dev/null +++ b/KAI-7B-v0.1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bbaa3948bb6c4606a9fecf848f9a2f03fe8f6cb57ad398923eef270f54ed73b +size 3182394048 diff --git a/KAI-7B-v0.1.IQ3_XS.gguf b/KAI-7B-v0.1.IQ3_XS.gguf new file mode 100644 index 0000000..7a8a978 --- /dev/null +++ b/KAI-7B-v0.1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334ceebfa6d13d1b58a1abeea5f960c0267aadbe79e19494e03fa207f64234d3 +size 3018816192 diff --git a/KAI-7B-v0.1.IQ4_XS.gguf b/KAI-7B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..3cd3c25 --- /dev/null +++ b/KAI-7B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ef9b629c4e269b7be1fddd39629b6f1ae8cca6785b61b5e3b32c880a15f693 +size 3944389312 diff --git a/KAI-7B-v0.1.Q2_K.gguf b/KAI-7B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..ebedb8e --- /dev/null +++ b/KAI-7B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266a92cefd7161c5b8df66ac39682f55a0264fd0dca4b256701ae4c5393096d4 +size 2719242944 diff --git a/KAI-7B-v0.1.Q3_K_L.gguf b/KAI-7B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..f2b3b7b --- /dev/null +++ b/KAI-7B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31cba638069a58fe60848bd86f98df4823f56a6af52572be371035fd9b6cb93f +size 3822025408 diff --git a/KAI-7B-v0.1.Q3_K_M.gguf b/KAI-7B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..82fcd0f --- /dev/null +++ b/KAI-7B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73ca93a9d662658e1b4240c2d403b4a921d97dbf9a1d55fe03d0dc732cc9056 +size 3518986944 diff --git a/KAI-7B-v0.1.Q3_K_S.gguf b/KAI-7B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..43c21b9 --- /dev/null +++ b/KAI-7B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07f45e09cd5401d474373a2e89cc885aeeb62c34e5dbd41b4e46bfbfac90a980 +size 3164568256 diff --git a/KAI-7B-v0.1.Q4_K_M.gguf b/KAI-7B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..d112a55 --- /dev/null +++ b/KAI-7B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6c4d03dbebcffedc865cdd98d87ec2182a080c1a17c38580837931f7d8bf95 +size 4368440000 diff --git a/KAI-7B-v0.1.Q4_K_S.gguf b/KAI-7B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..563fbd8 --- /dev/null +++ b/KAI-7B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c4861c7d84bbd5d02017ba617db55f166aa28da794f3187e834e04bcc3909f +size 4140374720 diff --git a/KAI-7B-v0.1.Q5_K_M.gguf b/KAI-7B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..c5295c7 --- /dev/null +++ b/KAI-7B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e61d42e5788deb801cadd48bfa37ff9c8a989d513af06c4c4c93fd6b074b46 +size 5131410112 diff --git a/KAI-7B-v0.1.Q5_K_S.gguf b/KAI-7B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..2bfd0dd --- /dev/null +++ b/KAI-7B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8c9b2267129aede56ee91c71bce59c60831a074c535188d5be56cb6feeda06 +size 4997716672 diff --git a/KAI-7B-v0.1.Q6_K.gguf b/KAI-7B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..2f8bbb0 --- /dev/null +++ b/KAI-7B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98597de238eb5da76ed26f2a021d9aa2780f46e9c01e6eef2761daa4b1cacab3 +size 5942065856 diff --git a/KAI-7B-v0.1.Q8_0.gguf b/KAI-7B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..cec7d16 --- /dev/null +++ b/KAI-7B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b32ae407accf9e4ea4d7b2ab1cb6dcb433dd026a15da9e58a932954dfa891287 +size 7695858368 diff --git a/KAI-7B-v0.1.f16.gguf b/KAI-7B-v0.1.f16.gguf new file mode 100644 index 0000000..2b86a42 --- /dev/null +++ b/KAI-7B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1296bcffcd8560f8e718b8a6a493820e7e8820e6c1e404cbc89edc627df46424 +size 14484732608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..29a1bd6 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Keynote-Technology/KAI-7B-v0.1 +datasets: +- Keynote-Technology/PLANE-2K +- togethercomputer/RedPajama-Data-V2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- code +- text-generation-inference +- pretrained +--- +## About + + + + + + +static quants of https://huggingface.co/Keynote-Technology/KAI-7B-v0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KAI-7B-v0.1-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/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-v0.1-GGUF/resolve/main/KAI-7B-v0.1.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. + +