From 4d88bedf269daa328b33f18dd25684e2685c989a Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 18 Sep 2026 04:28:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/CosMoE-Lisa-4x1b-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++++++ CosMoE-Lisa-4x1b.IQ4_XS.gguf | 3 ++ CosMoE-Lisa-4x1b.Q2_K.gguf | 3 ++ CosMoE-Lisa-4x1b.Q3_K_L.gguf | 3 ++ CosMoE-Lisa-4x1b.Q3_K_M.gguf | 3 ++ CosMoE-Lisa-4x1b.Q3_K_S.gguf | 3 ++ CosMoE-Lisa-4x1b.Q4_K_M.gguf | 3 ++ CosMoE-Lisa-4x1b.Q4_K_S.gguf | 3 ++ CosMoE-Lisa-4x1b.Q5_K_M.gguf | 3 ++ CosMoE-Lisa-4x1b.Q5_K_S.gguf | 3 ++ CosMoE-Lisa-4x1b.Q6_K.gguf | 3 ++ CosMoE-Lisa-4x1b.Q8_0.gguf | 3 ++ CosMoE-Lisa-4x1b.f16.gguf | 3 ++ README.md | 71 ++++++++++++++++++++++++++++++++++++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 CosMoE-Lisa-4x1b.IQ4_XS.gguf create mode 100644 CosMoE-Lisa-4x1b.Q2_K.gguf create mode 100644 CosMoE-Lisa-4x1b.Q3_K_L.gguf create mode 100644 CosMoE-Lisa-4x1b.Q3_K_M.gguf create mode 100644 CosMoE-Lisa-4x1b.Q3_K_S.gguf create mode 100644 CosMoE-Lisa-4x1b.Q4_K_M.gguf create mode 100644 CosMoE-Lisa-4x1b.Q4_K_S.gguf create mode 100644 CosMoE-Lisa-4x1b.Q5_K_M.gguf create mode 100644 CosMoE-Lisa-4x1b.Q5_K_S.gguf create mode 100644 CosMoE-Lisa-4x1b.Q6_K.gguf create mode 100644 CosMoE-Lisa-4x1b.Q8_0.gguf create mode 100644 CosMoE-Lisa-4x1b.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1cfc500 --- /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 +CosMoE-Lisa-4x1b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CosMoE-Lisa-4x1b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CosMoE-Lisa-4x1b.IQ4_XS.gguf b/CosMoE-Lisa-4x1b.IQ4_XS.gguf new file mode 100644 index 0000000..3f1cc21 --- /dev/null +++ b/CosMoE-Lisa-4x1b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d05bd49f0647194e6d2d19005f9a5cc9758752288ce94ee16e3b1b0bd698d19 +size 2902778944 diff --git a/CosMoE-Lisa-4x1b.Q2_K.gguf b/CosMoE-Lisa-4x1b.Q2_K.gguf new file mode 100644 index 0000000..add0e73 --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89436bfff82838b633c5ce240dfba52663ef58d800fc18596f85bdb680466272 +size 1978778688 diff --git a/CosMoE-Lisa-4x1b.Q3_K_L.gguf b/CosMoE-Lisa-4x1b.Q3_K_L.gguf new file mode 100644 index 0000000..bdb2f94 --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace3e7b2fc1a173865a13fb82912e6346b983315d5e2bfd63236907886018f47 +size 2800178240 diff --git a/CosMoE-Lisa-4x1b.Q3_K_M.gguf b/CosMoE-Lisa-4x1b.Q3_K_M.gguf new file mode 100644 index 0000000..448814e --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe6bbd761188b06a4f7836290d7e209c29f6174fba8693fab2c484b641e792c +size 2583123008 diff --git a/CosMoE-Lisa-4x1b.Q3_K_S.gguf b/CosMoE-Lisa-4x1b.Q3_K_S.gguf new file mode 100644 index 0000000..aea8898 --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e363752b9e59f8c0e2f8321ff0c3d9756ff8385a6fb858dd21f0496af3b7214f +size 2333037632 diff --git a/CosMoE-Lisa-4x1b.Q4_K_M.gguf b/CosMoE-Lisa-4x1b.Q4_K_M.gguf new file mode 100644 index 0000000..e7afd8f --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3573fefe05e38ab46597adebb1d5599cf79f05c972df805ae8bc25c0f0f724e3 +size 3257541696 diff --git a/CosMoE-Lisa-4x1b.Q4_K_S.gguf b/CosMoE-Lisa-4x1b.Q4_K_S.gguf new file mode 100644 index 0000000..8514ade --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43a4ecaa9b823c16dd8dd11cc318388dacbad080b92ce88c79fad47e15efe95 +size 3064210496 diff --git a/CosMoE-Lisa-4x1b.Q5_K_M.gguf b/CosMoE-Lisa-4x1b.Q5_K_M.gguf new file mode 100644 index 0000000..b3b00f0 --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4055077a18f9a3f9b84886922dc02531c5a8cfc449c82173d870fc756d08b3 +size 3813090368 diff --git a/CosMoE-Lisa-4x1b.Q5_K_S.gguf b/CosMoE-Lisa-4x1b.Q5_K_S.gguf new file mode 100644 index 0000000..3d4e47a --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ed8d485f70c464afb1572a6c40d2bcb4816b5a1e19786c8c9eb18008b596ee +size 3699450944 diff --git a/CosMoE-Lisa-4x1b.Q6_K.gguf b/CosMoE-Lisa-4x1b.Q6_K.gguf new file mode 100644 index 0000000..ff56892 --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7363af66f4268d0439ecf25118ebaa336f8cc06a33d422245b413ab5058c2908 +size 4403360832 diff --git a/CosMoE-Lisa-4x1b.Q8_0.gguf b/CosMoE-Lisa-4x1b.Q8_0.gguf new file mode 100644 index 0000000..60c9b2c --- /dev/null +++ b/CosMoE-Lisa-4x1b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c49cebc865e7e2e0dccbead26f3b724efdd8f454507eb43a962eaa61c45e30c +size 5702833216 diff --git a/CosMoE-Lisa-4x1b.f16.gguf b/CosMoE-Lisa-4x1b.f16.gguf new file mode 100644 index 0000000..cb05299 --- /dev/null +++ b/CosMoE-Lisa-4x1b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61084d0f3b10f3150daf43b3a4e9f5746ab930ff9bb75211a9087113c157ac8e +size 10733048896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..17074a1 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Lambent/CosMoE-Lisa-4x1b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Lambent/CosMoE-Lisa-4x1b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CosMoE-Lisa-4x1b-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/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q2_K.gguf) | Q2_K | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q3_K_S.gguf) | Q3_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q3_K_M.gguf) | Q3_K_M | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q3_K_L.gguf) | Q3_K_L | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.IQ4_XS.gguf) | IQ4_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q4_K_S.gguf) | Q4_K_S | 3.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q4_K_M.gguf) | Q4_K_M | 3.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q5_K_S.gguf) | Q5_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q5_K_M.gguf) | Q5_K_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q6_K.gguf) | Q6_K | 4.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.Q8_0.gguf) | Q8_0 | 5.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CosMoE-Lisa-4x1b-GGUF/resolve/main/CosMoE-Lisa-4x1b.f16.gguf) | f16 | 10.8 | 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. + +