commit 4d2eeb2222a3ee740373b448e798dc9c57304751 Author: ModelHub XC Date: Sat Jun 13 06:02:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KageAI-7B-v1.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..df6b9f1 --- /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 +KageAI-7B-v1.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KageAI-7B-v1.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KageAI-7B-v1.2.IQ4_XS.gguf b/KageAI-7B-v1.2.IQ4_XS.gguf new file mode 100644 index 0000000..56ecf0d --- /dev/null +++ b/KageAI-7B-v1.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72daf8a7bac88e82f2d822fc9f7a89e2c26cda5812b259a38580c000c48ef8bc +size 3948663872 diff --git a/KageAI-7B-v1.2.Q2_K.gguf b/KageAI-7B-v1.2.Q2_K.gguf new file mode 100644 index 0000000..2810479 --- /dev/null +++ b/KageAI-7B-v1.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62abb78f49b32ad217f7ce93e20bcc31bcfafc4643b8756b9547b8c7daa88905 +size 2722878528 diff --git a/KageAI-7B-v1.2.Q3_K_L.gguf b/KageAI-7B-v1.2.Q3_K_L.gguf new file mode 100644 index 0000000..fb48ad7 --- /dev/null +++ b/KageAI-7B-v1.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86852f893de384528f9e317932ed98cb55f70dd28b0d844b026ada60828afb39 +size 3825980480 diff --git a/KageAI-7B-v1.2.Q3_K_M.gguf b/KageAI-7B-v1.2.Q3_K_M.gguf new file mode 100644 index 0000000..2134362 --- /dev/null +++ b/KageAI-7B-v1.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6967f501a247b8d8bb889ec60d521f8d20c1c0dcacd00a26c5abb04a9350a4ea +size 3522942016 diff --git a/KageAI-7B-v1.2.Q3_K_S.gguf b/KageAI-7B-v1.2.Q3_K_S.gguf new file mode 100644 index 0000000..69d4639 --- /dev/null +++ b/KageAI-7B-v1.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bebe71af6fdc81c0d5a951fbeb59bc099b2b89941dd0d3f4287ccf59c44b043f +size 3168523328 diff --git a/KageAI-7B-v1.2.Q4_K_M.gguf b/KageAI-7B-v1.2.Q4_K_M.gguf new file mode 100644 index 0000000..e887675 --- /dev/null +++ b/KageAI-7B-v1.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67825ad97cf7da4bcfa2d805c75db6c47461b7e512c673b03b68abe5b7acd261 +size 4372812864 diff --git a/KageAI-7B-v1.2.Q4_K_S.gguf b/KageAI-7B-v1.2.Q4_K_S.gguf new file mode 100644 index 0000000..973b6f7 --- /dev/null +++ b/KageAI-7B-v1.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf14706a271271ca6a461b2704a4d917fc317454d5af6895f2c89d6a2a0b3150 +size 4144747584 diff --git a/KageAI-7B-v1.2.Q5_K_M.gguf b/KageAI-7B-v1.2.Q5_K_M.gguf new file mode 100644 index 0000000..c1abb41 --- /dev/null +++ b/KageAI-7B-v1.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aebdb10e68e0a5bb3399d4da70f1362bcf7bbd7a75b05e2c5013ca7d6202960 +size 5136176192 diff --git a/KageAI-7B-v1.2.Q5_K_S.gguf b/KageAI-7B-v1.2.Q5_K_S.gguf new file mode 100644 index 0000000..ea2bcc6 --- /dev/null +++ b/KageAI-7B-v1.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcddc21c97733660c8497592067af6515330ae06e4655d6844837617358c6f23 +size 5002482752 diff --git a/KageAI-7B-v1.2.Q6_K.gguf b/KageAI-7B-v1.2.Q6_K.gguf new file mode 100644 index 0000000..1182570 --- /dev/null +++ b/KageAI-7B-v1.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ba054f42d05d57ab355b7932b3c7e2cfda1012ff7b0a3d83787bc5aea1ae33 +size 5947249728 diff --git a/KageAI-7B-v1.2.Q8_0.gguf b/KageAI-7B-v1.2.Q8_0.gguf new file mode 100644 index 0000000..6a8f291 --- /dev/null +++ b/KageAI-7B-v1.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a80663d0d17f82fb57f075a14861aafab3213d6c449d62b0d30fdff76a7cd5 +size 7702565952 diff --git a/KageAI-7B-v1.2.f16.gguf b/KageAI-7B-v1.2.f16.gguf new file mode 100644 index 0000000..488ce78 --- /dev/null +++ b/KageAI-7B-v1.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48fed2cf81540744fdfaeab06ddbcce8418d0cddb0523c93dda310737bae7040 +size 14497338432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e00d874 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: kagelabs/KageAI-7B-v1.2 +datasets: +- teknium/OpenHermes-2.5 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- galore +- tech-specialist +--- +## About + + + + + + + + + +static quants of https://huggingface.co/kagelabs/KageAI-7B-v1.2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KageAI-7B-v1.2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KageAI-7B-v1.2-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/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KageAI-7B-v1.2-GGUF/resolve/main/KageAI-7B-v1.2.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. + +