commit 77d01a42d9b966bcca4b667a4642fd13d6acdf36 Author: ModelHub XC Date: Thu Jun 11 08:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KAI-7B-Instruct-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b01aa7b --- /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-Instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAI-7B-Instruct-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KAI-7B-Instruct-v0.1.IQ3_M.gguf b/KAI-7B-Instruct-v0.1.IQ3_M.gguf new file mode 100644 index 0000000..033f706 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04bb0341c795289a73896638c7a52fea91989e440a182d8be1422ef259e7f884 +size 3284892864 diff --git a/KAI-7B-Instruct-v0.1.IQ3_S.gguf b/KAI-7B-Instruct-v0.1.IQ3_S.gguf new file mode 100644 index 0000000..d4cf7cb --- /dev/null +++ b/KAI-7B-Instruct-v0.1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd6e3f6797b5a07903f4e44aeeae5ad46219f47236a340c0e544fb69bd548ef +size 3182394560 diff --git a/KAI-7B-Instruct-v0.1.IQ3_XS.gguf b/KAI-7B-Instruct-v0.1.IQ3_XS.gguf new file mode 100644 index 0000000..8e5883e --- /dev/null +++ b/KAI-7B-Instruct-v0.1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb8cea80e39483dce7bb27aee1ccf5dd9a4d0eaf60d5d7620f0568096d5c7c0 +size 3018816704 diff --git a/KAI-7B-Instruct-v0.1.IQ4_XS.gguf b/KAI-7B-Instruct-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..0d89a3d --- /dev/null +++ b/KAI-7B-Instruct-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b7d6931bf9bc98f411063c663db10affa34d27d577af259962f0d43137f12d +size 3944389824 diff --git a/KAI-7B-Instruct-v0.1.Q2_K.gguf b/KAI-7B-Instruct-v0.1.Q2_K.gguf new file mode 100644 index 0000000..29ad119 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61757d5adc871e7b16cbe48e1dcbc0e97665a8854b358da1648f40eaf062cfaa +size 2719243456 diff --git a/KAI-7B-Instruct-v0.1.Q3_K_L.gguf b/KAI-7B-Instruct-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..9e6d866 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f991950d3888798b2240a90cb331303ced719e615e2d9689b6e4117769daead +size 3822025920 diff --git a/KAI-7B-Instruct-v0.1.Q3_K_M.gguf b/KAI-7B-Instruct-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..9a881fe --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8a7b7a1b1455b40f2b012cd8b2e9442a955c312e9125c516b6cb659ee0126c +size 3518987456 diff --git a/KAI-7B-Instruct-v0.1.Q3_K_S.gguf b/KAI-7B-Instruct-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..ed10253 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a5accab345bfcccf1636e01f2e5d2c60dd7910d6f00266c35ee48ca6bd0ffb +size 3164568768 diff --git a/KAI-7B-Instruct-v0.1.Q4_K_M.gguf b/KAI-7B-Instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..668e75d --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48cdfacb666ee516d9920940ae468ddd30cf8d4ad16b9537967423f121fdefa8 +size 4368440512 diff --git a/KAI-7B-Instruct-v0.1.Q4_K_S.gguf b/KAI-7B-Instruct-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..95d66e7 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d28eaf04f9283d5d9c37d7bcabb2220b1a2080e699d4799e78b9babc9c3bc47 +size 4140375232 diff --git a/KAI-7B-Instruct-v0.1.Q5_K_M.gguf b/KAI-7B-Instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..c478d9f --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f43239640265ac871ed1e8ac85559b44284fd24f8288ec40a3c449a3e88603dc +size 5131410624 diff --git a/KAI-7B-Instruct-v0.1.Q5_K_S.gguf b/KAI-7B-Instruct-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..2ebd9cf --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2801f7d90ce09c4978cd503b859dc51a5ee4cf388b5d386116640b819a11f99c +size 4997717184 diff --git a/KAI-7B-Instruct-v0.1.Q6_K.gguf b/KAI-7B-Instruct-v0.1.Q6_K.gguf new file mode 100644 index 0000000..b09e9a5 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9080827116ae388a6d0f2d19c9fb848324d686b52495f37af65dda20fa36f1fb +size 5942066368 diff --git a/KAI-7B-Instruct-v0.1.Q8_0.gguf b/KAI-7B-Instruct-v0.1.Q8_0.gguf new file mode 100644 index 0000000..4631b67 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d8ceef5488fe2d2fd01a79e6cb012a1b6fd9a6b0cce26b003ffd6319b7d75d +size 7695858880 diff --git a/KAI-7B-Instruct-v0.1.f16.gguf b/KAI-7B-Instruct-v0.1.f16.gguf new file mode 100644 index 0000000..5e2b0a3 --- /dev/null +++ b/KAI-7B-Instruct-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c808f6fffe3ad0079d05fd9bd3b157945b74f0798c7b6366f76cec54e301d6 +size 14484733120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..974e3e7 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Keynote-Technology/KAI-7B-Instruct-v0.1 +datasets: +- Keynote-Technology/PLANE-2K +- togethercomputer/RedPajama-Data-V2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- finetuned +- Instruct +- code +--- +## About + + + + + + +static quants of https://huggingface.co/Keynote-Technology/KAI-7B-Instruct-v0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KAI-7B-Instruct-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-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-v0.1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KAI-7B-Instruct-v0.1-GGUF/resolve/main/KAI-7B-Instruct-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. + +