commit 188a22f5d63806b90000e7a7e30cf05180a442bf Author: ModelHub XC Date: Sun Sep 6 18:36:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Apertus-v1.1-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f8dfc1f --- /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 +Apertus-v1.1-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-v1.1-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Apertus-v1.1-1.5B.IQ4_XS.gguf b/Apertus-v1.1-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..460b2f9 --- /dev/null +++ b/Apertus-v1.1-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1420b69b84e390c5e36147ddf9613261701d58111459d767cab38918e0d0a1 +size 898389600 diff --git a/Apertus-v1.1-1.5B.Q2_K.gguf b/Apertus-v1.1-1.5B.Q2_K.gguf new file mode 100644 index 0000000..3bb7aeb --- /dev/null +++ b/Apertus-v1.1-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e48dead8c36118ce0a721eab834cbede9fb758db533cabdb0fdbf22c2198fa +size 687363680 diff --git a/Apertus-v1.1-1.5B.Q3_K_L.gguf b/Apertus-v1.1-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..6eec5d4 --- /dev/null +++ b/Apertus-v1.1-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6038fe56161b1778465b369b9741acb3f668f96b0284766e4bd2f49acebc865 +size 887248480 diff --git a/Apertus-v1.1-1.5B.Q3_K_M.gguf b/Apertus-v1.1-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..c110b10 --- /dev/null +++ b/Apertus-v1.1-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d94393b04dd27432528c65f00cdca341ef44249aea6714824cfdecf10a70d7 +size 829838944 diff --git a/Apertus-v1.1-1.5B.Q3_K_S.gguf b/Apertus-v1.1-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..9cc6e7c --- /dev/null +++ b/Apertus-v1.1-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd280661618cc463babf454d5e11f12255d77fd54b048c5491b8cab18c559a6 +size 761812576 diff --git a/Apertus-v1.1-1.5B.Q4_K_M.gguf b/Apertus-v1.1-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..8f8d7a4 --- /dev/null +++ b/Apertus-v1.1-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a650c33b87554f7820c142246185858ec3ec1c7cb52075d9427a25a3919620d +size 980768352 diff --git a/Apertus-v1.1-1.5B.Q4_K_S.gguf b/Apertus-v1.1-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..f1a6d80 --- /dev/null +++ b/Apertus-v1.1-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d909e349b5b29b007384a93b486a4619f663c91f73dc787d0e08d715d2c5933 +size 933516896 diff --git a/Apertus-v1.1-1.5B.Q5_K_M.gguf b/Apertus-v1.1-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..c642f68 --- /dev/null +++ b/Apertus-v1.1-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6f5ebb73cfb951620471a97621b89c0e8cd1d346eb9c4b72188f497e7329a8 +size 1109743200 diff --git a/Apertus-v1.1-1.5B.Q5_K_S.gguf b/Apertus-v1.1-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..c153074 --- /dev/null +++ b/Apertus-v1.1-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458e81dee8c62f1e26b8166cc5026256f21aae018412e3e29b19683ca7d30686 +size 1081890400 diff --git a/Apertus-v1.1-1.5B.Q6_K.gguf b/Apertus-v1.1-1.5B.Q6_K.gguf new file mode 100644 index 0000000..6030cda --- /dev/null +++ b/Apertus-v1.1-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4a258ead339de3fe1192054ba6a11e8d34bf0e2f3fd5cf0eac65606ce3227ff +size 1246778976 diff --git a/Apertus-v1.1-1.5B.Q8_0.gguf b/Apertus-v1.1-1.5B.Q8_0.gguf new file mode 100644 index 0000000..f028ba0 --- /dev/null +++ b/Apertus-v1.1-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0924c22d8181c52e7a657b030063337feebedc84f7d0bb28cca714405ceaed +size 1612469856 diff --git a/Apertus-v1.1-1.5B.f16.gguf b/Apertus-v1.1-1.5B.f16.gguf new file mode 100644 index 0000000..416f444 --- /dev/null +++ b/Apertus-v1.1-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff810ff22fdde0c7c8f1f345975332d7b381f8afe3fafd3e759cf3eb7243fc1d +size 3028047456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ff6490d --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: swiss-ai/Apertus-v1.1-1.5B +extra_gated_button_content: Submit +extra_gated_fields: + Affiliation: text + By clicking Submit below I accept the terms of use: checkbox + Country: country + Your Name: text + geo: ip_location +extra_gated_prompt: "### Apertus LLM Acceptable Use Policy \n(1.0 | September 1, + 2025)\n\"Agreement\" The Swiss National AI Institute (SNAI) is a partnership between + the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL. \n\nBy using + the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and + EPFL against any third-party claims arising from your use of Apertus LLM. \n\nThe + training data and the Apertus LLM may contain or generate information that directly + or indirectly refers to an identifiable individual (Personal Data). You process + Personal Data as independent controller in accordance with applicable data protection + law. SNAI will regularly provide a file with hash values for download which you + can apply as an output filter to your use of our Apertus LLM. The file reflects + data protection deletion requests which have been addressed to SNAI as the developer + of the Apertus LLM. It allows you to remove Personal Data contained in the model + output. We strongly advise downloading and applying this output filter from SNAI + every six months following the release of the model. " +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- multilingual +- compliant +- swiss-ai +- apertus +--- +## About + + + + + + + + + +static quants of https://huggingface.co/swiss-ai/Apertus-v1.1-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Apertus-v1.1-1.5B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-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/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Apertus-v1.1-1.5B-GGUF/resolve/main/Apertus-v1.1-1.5B.f16.gguf) | f16 | 3.1 | 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. + +