commit 349970f4508034581a07027e6ccdbf923e673f50 Author: ModelHub XC Date: Thu Sep 3 23:12:44 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/kheops_compressed-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..74d1f2a --- /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 +kheops_compressed.f16.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kheops_compressed.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5d47a0e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: kheopss/kheops_compressed +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/kheopss/kheops_compressed + + +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/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.IQ3_XS.gguf) | IQ3_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.IQ3_S.gguf) | IQ3_S | 0.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.IQ3_M.gguf) | IQ3_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q5_K_S.gguf) | Q5_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q5_K_M.gguf) | Q5_K_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.Q8_0.gguf) | Q8_0 | 0.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/kheops_compressed-GGUF/resolve/main/kheops_compressed.f16.gguf) | f16 | 0.7 | 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/kheops_compressed.IQ3_M.gguf b/kheops_compressed.IQ3_M.gguf new file mode 100644 index 0000000..df926cb --- /dev/null +++ b/kheops_compressed.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8d8157642ba5635b634bf8cf119a77ece2e1e6ce1a9ca74ab639450921811d +size 155773440 diff --git a/kheops_compressed.IQ3_S.gguf b/kheops_compressed.IQ3_S.gguf new file mode 100644 index 0000000..5c3ccfc --- /dev/null +++ b/kheops_compressed.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32daa833a2e12d24e46eb5f33fb1ec502cacd552b165bfd9427d60afff39281 +size 152431104 diff --git a/kheops_compressed.IQ3_XS.gguf b/kheops_compressed.IQ3_XS.gguf new file mode 100644 index 0000000..f81ab8d --- /dev/null +++ b/kheops_compressed.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b788114038205b51ba6ca2617f87a883c839c0135a904cb39b02abed4f75749 +size 149137920 diff --git a/kheops_compressed.IQ4_XS.gguf b/kheops_compressed.IQ4_XS.gguf new file mode 100644 index 0000000..c2e789e --- /dev/null +++ b/kheops_compressed.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5017c3860daf0df4d94b78413dc24299d62e588e567fa3ec2c52cdb489c39d1b +size 171067904 diff --git a/kheops_compressed.Q2_K.gguf b/kheops_compressed.Q2_K.gguf new file mode 100644 index 0000000..795702b --- /dev/null +++ b/kheops_compressed.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41406b49359c0f0b03d54a900edddbbadc5510d58e0601c5701f3eba83caac7b +size 136350208 diff --git a/kheops_compressed.Q3_K_L.gguf b/kheops_compressed.Q3_K_L.gguf new file mode 100644 index 0000000..1a4f4df --- /dev/null +++ b/kheops_compressed.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d667d8a32f397ae3623339685221d2a915f6a1e481c9b91dfef331a32a73c2 +size 165259776 diff --git a/kheops_compressed.Q3_K_M.gguf b/kheops_compressed.Q3_K_M.gguf new file mode 100644 index 0000000..ce82cd3 --- /dev/null +++ b/kheops_compressed.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c373c30347495043bb5686e59684906d383110a3c7b747321861657ff48e00d +size 161049088 diff --git a/kheops_compressed.Q3_K_S.gguf b/kheops_compressed.Q3_K_S.gguf new file mode 100644 index 0000000..5505ff8 --- /dev/null +++ b/kheops_compressed.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114697f68c3ce8c67d3e792c88401e34778fd475b993b01ba233d2d3d4ca223c +size 152431104 diff --git a/kheops_compressed.Q4_K_M.gguf b/kheops_compressed.Q4_K_M.gguf new file mode 100644 index 0000000..8e40100 --- /dev/null +++ b/kheops_compressed.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0edf0585f1129b75ab6c4d67461e4a20ab8711884827b896304fafa005fa40f6 +size 186337792 diff --git a/kheops_compressed.Q4_K_S.gguf b/kheops_compressed.Q4_K_S.gguf new file mode 100644 index 0000000..fef3639 --- /dev/null +++ b/kheops_compressed.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4781dc955342194e0954fe78aa4594e5d3fe12faf1045820579e2965e286dbfe +size 182602240 diff --git a/kheops_compressed.Q5_K_M.gguf b/kheops_compressed.Q5_K_M.gguf new file mode 100644 index 0000000..891a381 --- /dev/null +++ b/kheops_compressed.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d9406c9c0c4ef3c3f9c88d641fd1edeacd2a889d85b14fe9c5113fb350aa50 +size 210160128 diff --git a/kheops_compressed.Q5_K_S.gguf b/kheops_compressed.Q5_K_S.gguf new file mode 100644 index 0000000..3b5042a --- /dev/null +++ b/kheops_compressed.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81131f4e8991f1f3c5424d3514dbe58a5678fb7520e73daa1a7758a75ce901a4 +size 206080512 diff --git a/kheops_compressed.Q6_K.gguf b/kheops_compressed.Q6_K.gguf new file mode 100644 index 0000000..b8ce12b --- /dev/null +++ b/kheops_compressed.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54351e5be7f1958ca77633598b3e3c56d5ce0324234e755c97157d9e2c3abbbd +size 241019392 diff --git a/kheops_compressed.Q8_0.gguf b/kheops_compressed.Q8_0.gguf new file mode 100644 index 0000000..60c34f6 --- /dev/null +++ b/kheops_compressed.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f3d5363f2514aea0067ad03d515f1583fa26da0192b408466999c3f4524a76 +size 301332992 diff --git a/kheops_compressed.f16.gguf b/kheops_compressed.f16.gguf new file mode 100644 index 0000000..50dc7dd --- /dev/null +++ b/kheops_compressed.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:282a19229323641152d6b87f5572bcf111a755a6e9df214cf522bb37a0f933b9 +size 566508032