commit f0c6aaa1fe613a878ea8482bf1c6617f95f70617 Author: ModelHub XC Date: Sat May 9 02:03:49 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/KRAG-SOTA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fba5dea --- /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 +KRAG-SOTA.f16.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KRAG-SOTA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KRAG-SOTA.IQ4_XS.gguf b/KRAG-SOTA.IQ4_XS.gguf new file mode 100644 index 0000000..0d8623e --- /dev/null +++ b/KRAG-SOTA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a51cd6364671eaeb7ad030420171651779f72f5591ae26d7b9e7da7fc1a58636 +size 4484393824 diff --git a/KRAG-SOTA.Q2_K.gguf b/KRAG-SOTA.Q2_K.gguf new file mode 100644 index 0000000..7148cf0 --- /dev/null +++ b/KRAG-SOTA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3bf7e9622add30856dca8be1a93a2c43e02786171c4246e98627e5ca1c966d +size 3179159968 diff --git a/KRAG-SOTA.Q3_K_L.gguf b/KRAG-SOTA.Q3_K_L.gguf new file mode 100644 index 0000000..c0532af --- /dev/null +++ b/KRAG-SOTA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4512244856bd4628bc1e0309e2fb1968d3941262ea34891984770410f5c90cce +size 4321986176 diff --git a/KRAG-SOTA.Q3_K_M.gguf b/KRAG-SOTA.Q3_K_M.gguf new file mode 100644 index 0000000..a273bcc --- /dev/null +++ b/KRAG-SOTA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3f0663f62978007739ebf43c88f79e7cdf6b77a694701fe91b11d3d5b5a8a3 +size 4018947712 diff --git a/KRAG-SOTA.Q3_K_S.gguf b/KRAG-SOTA.Q3_K_S.gguf new file mode 100644 index 0000000..49efbd5 --- /dev/null +++ b/KRAG-SOTA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ccaf5e39c3cd4edd624c9e3f7fee21ee9964a4a458ef1f85418161203644adc +size 3664529024 diff --git a/KRAG-SOTA.Q4_K_M.gguf b/KRAG-SOTA.Q4_K_M.gguf new file mode 100644 index 0000000..d9ba6fd --- /dev/null +++ b/KRAG-SOTA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c91eea9f489f91f3468a2e9441c0eb60860f8d40cddc8381115bc49506cbda4 +size 4920765664 diff --git a/KRAG-SOTA.Q4_K_S.gguf b/KRAG-SOTA.Q4_K_S.gguf new file mode 100644 index 0000000..27df207 --- /dev/null +++ b/KRAG-SOTA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:732fbd8195da180da176396a4cda160cfdabb36e45f597538f1e8a6faf22dbcf +size 4692700384 diff --git a/KRAG-SOTA.Q5_K_M.gguf b/KRAG-SOTA.Q5_K_M.gguf new file mode 100644 index 0000000..5b2f9c3 --- /dev/null +++ b/KRAG-SOTA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c3c5ee04d0c54bf1330e80b907eb41e6ab2e6c2b0fecd69269ec547800eee4 +size 5733020384 diff --git a/KRAG-SOTA.Q5_K_S.gguf b/KRAG-SOTA.Q5_K_S.gguf new file mode 100644 index 0000000..b1a075d --- /dev/null +++ b/KRAG-SOTA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e54ec6ecf80164060397784d639b42bbc92aac3e45ad4d51b440da2644aa5c8 +size 5599326944 diff --git a/KRAG-SOTA.Q6_K.gguf b/KRAG-SOTA.Q6_K.gguf new file mode 100644 index 0000000..0f9c014 --- /dev/null +++ b/KRAG-SOTA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb21f7918c36b6dc03895d26609c3852b5a6e5bbbabc9e1d6d5ad445538bd32 +size 6596041024 diff --git a/KRAG-SOTA.Q8_0.gguf b/KRAG-SOTA.Q8_0.gguf new file mode 100644 index 0000000..93677bc --- /dev/null +++ b/KRAG-SOTA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5153a8d756c82236ee786ebd2fe0a08edb48598bc8a01e4857f56a19e7f88b73 +size 8540811392 diff --git a/KRAG-SOTA.f16.gguf b/KRAG-SOTA.f16.gguf new file mode 100644 index 0000000..4ea6aea --- /dev/null +++ b/KRAG-SOTA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcedb715a04d9076ff5f48fc212396c04e2dc2327185734ff3cc90f854c5b5c8 +size 16068954752 diff --git a/README.md b/README.md new file mode 100644 index 0000000..907f520 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: overfit-brothers/KRAG-SOTA +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/overfit-brothers/KRAG-SOTA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KRAG-SOTA-GGUF).*** + +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/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KRAG-SOTA-GGUF/resolve/main/KRAG-SOTA.f16.gguf) | f16 | 16.2 | 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. + +