commit 83620f276f5f36ad2d9be9c33ba058f745fbdf1e Author: ModelHub XC Date: Wed Jul 15 16:15:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: unsloth/Apertus-8B-Instruct-2509-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..67127bd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,75 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text + +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb 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 +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +Apertus-8B-Instruct-2509-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-BF16.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +imatrix_unsloth.gguf_file filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Apertus-8B-Instruct-2509-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Apertus-8B-Instruct-2509-BF16.gguf b/Apertus-8B-Instruct-2509-BF16.gguf new file mode 100644 index 0000000..1d3768a --- /dev/null +++ b/Apertus-8B-Instruct-2509-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c304abf37a80b1022244f2fcef5b2df316a8959ab46ac1f563e2358fc26e140 +size 16115119072 diff --git a/Apertus-8B-Instruct-2509-IQ4_NL.gguf b/Apertus-8B-Instruct-2509-IQ4_NL.gguf new file mode 100644 index 0000000..6abd8b6 --- /dev/null +++ b/Apertus-8B-Instruct-2509-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220cb2dc4cf0f962dd78f3bf9e02dbd05eb80746c24a9dda7053535372afb9b5 +size 4694029568 diff --git a/Apertus-8B-Instruct-2509-IQ4_XS.gguf b/Apertus-8B-Instruct-2509-IQ4_XS.gguf new file mode 100644 index 0000000..015c987 --- /dev/null +++ b/Apertus-8B-Instruct-2509-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52f829684e000fc52f4fac4d0259adb6424ae94f18caf2ca3210dd770cd823f7 +size 4480120064 diff --git a/Apertus-8B-Instruct-2509-Q2_K.gguf b/Apertus-8B-Instruct-2509-Q2_K.gguf new file mode 100644 index 0000000..a13350c --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bccebcb5a803265ef001cc25a22cd66b86bee339df0d9b24fc9c00848b10df8 +size 3287889152 diff --git a/Apertus-8B-Instruct-2509-Q2_K_L.gguf b/Apertus-8B-Instruct-2509-Q2_K_L.gguf new file mode 100644 index 0000000..85ec546 --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25f03b1302e8f3fd661d3089b71687408c52bff7c53da629a0565d0c03e0181 +size 3413718272 diff --git a/Apertus-8B-Instruct-2509-Q3_K_M.gguf b/Apertus-8B-Instruct-2509-Q3_K_M.gguf new file mode 100644 index 0000000..0728dc6 --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5988394272982041c6f37f223e487daad087b840e4c0861975c39971986510 +size 4165547264 diff --git a/Apertus-8B-Instruct-2509-Q3_K_S.gguf b/Apertus-8B-Instruct-2509-Q3_K_S.gguf new file mode 100644 index 0000000..cee7bc9 --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24561aedfd2f086490d4eb0ea82b33d8b5becce6b8587ecf5ab996aa69a445f1 +size 3679008000 diff --git a/Apertus-8B-Instruct-2509-Q4_0.gguf b/Apertus-8B-Instruct-2509-Q4_0.gguf new file mode 100644 index 0000000..0ebd526 --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8dc1b62443923837bca3b883b3e6fb122e0a157b07e1a65195bdf4178bb8bb +size 4699272448 diff --git a/Apertus-8B-Instruct-2509-Q4_1.gguf b/Apertus-8B-Instruct-2509-Q4_1.gguf new file mode 100644 index 0000000..f6df4cd --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e86e2e47dbf6c75b02b17920b38b14a613fcf28dea5ebde1f589f6d42fec77 +size 5147014400 diff --git a/Apertus-8B-Instruct-2509-Q4_K_M.gguf b/Apertus-8B-Instruct-2509-Q4_K_M.gguf new file mode 100644 index 0000000..0e84fb5 --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e7f0eb5a1d33e1a8ea4e7fdd2363764e0465061dd92962e0073aec31a7944d +size 5057885440 diff --git a/Apertus-8B-Instruct-2509-Q4_K_S.gguf b/Apertus-8B-Instruct-2509-Q4_K_S.gguf new file mode 100644 index 0000000..6b7228a --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faadcc3cb590188bda85dc5293992a0d7a9d5d38fce4652898801c4bca771e11 +size 4723389696 diff --git a/Apertus-8B-Instruct-2509-Q5_K_M.gguf b/Apertus-8B-Instruct-2509-Q5_K_M.gguf new file mode 100644 index 0000000..9e14d16 --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5f3ace9bd5ba476c3463de26e777f84016fd215dceb9ef9159938cc9775334 +size 5812860160 diff --git a/Apertus-8B-Instruct-2509-Q5_K_S.gguf b/Apertus-8B-Instruct-2509-Q5_K_S.gguf new file mode 100644 index 0000000..acc983c --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c1df03bc1d1f7ad0b857dd05fc1a799aa68e58c648b169a4629db3135cd2c9 +size 5616776448 diff --git a/Apertus-8B-Instruct-2509-Q6_K.gguf b/Apertus-8B-Instruct-2509-Q6_K.gguf new file mode 100644 index 0000000..6edfda2 --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc60c13413199c912d98d4c4d9b1a1b325beafeec8f898cf73c2fd2ad45dad5a +size 6615020800 diff --git a/Apertus-8B-Instruct-2509-Q8_0.gguf b/Apertus-8B-Instruct-2509-Q8_0.gguf new file mode 100644 index 0000000..b59c7bf --- /dev/null +++ b/Apertus-8B-Instruct-2509-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72fe8b0421884949aad157c1e19e249b6e52069b2eca98b41ebe105beb4a3dfc +size 8565372160 diff --git a/Apertus-8B-Instruct-2509-UD-IQ1_M.gguf b/Apertus-8B-Instruct-2509-UD-IQ1_M.gguf new file mode 100644 index 0000000..368dce4 --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129b67d083f27d6ad24d114827febd6802befdce3d7999f418250ef91a06d241 +size 2348758272 diff --git a/Apertus-8B-Instruct-2509-UD-IQ1_S.gguf b/Apertus-8B-Instruct-2509-UD-IQ1_S.gguf new file mode 100644 index 0000000..5a04543 --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f37344bc9fe6b8e33bd27231930c7ed05e2ccbffe001a39e9daa21ca9bda29 +size 2230400256 diff --git a/Apertus-8B-Instruct-2509-UD-IQ2_M.gguf b/Apertus-8B-Instruct-2509-UD-IQ2_M.gguf new file mode 100644 index 0000000..253fba6 --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7fe8a14fdef0ef142d01f91c37dd78be56af568bff949ab123e4cfcee1785fb +size 3026105600 diff --git a/Apertus-8B-Instruct-2509-UD-IQ2_XXS.gguf b/Apertus-8B-Instruct-2509-UD-IQ2_XXS.gguf new file mode 100644 index 0000000..f44ddd5 --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967866208e670fb26af25e7fd8b1f08c310e00d1ac535f3b9a92f2f5651576d8 +size 2552247552 diff --git a/Apertus-8B-Instruct-2509-UD-IQ3_XXS.gguf b/Apertus-8B-Instruct-2509-UD-IQ3_XXS.gguf new file mode 100644 index 0000000..807716b --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b6e7fca4c828ac1ae70a4ffdcad29fdf366d434a9ffc1b894ca11e5fe7cdc4 +size 3356538112 diff --git a/Apertus-8B-Instruct-2509-UD-Q2_K_XL.gguf b/Apertus-8B-Instruct-2509-UD-Q2_K_XL.gguf new file mode 100644 index 0000000..fe22de0 --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-Q2_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2660cf8b8cf94fe8a6b06c1d88f9ebdd8677746a6fdf14a2f46fc64af9fd194e +size 3501372672 diff --git a/Apertus-8B-Instruct-2509-UD-Q3_K_XL.gguf b/Apertus-8B-Instruct-2509-UD-Q3_K_XL.gguf new file mode 100644 index 0000000..f8cae32 --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18cef5d31dbe600f5cc341a6738437d93b37e557edd5bd11f276ae8f1bd9638 +size 4347770112 diff --git a/Apertus-8B-Instruct-2509-UD-Q4_K_XL.gguf b/Apertus-8B-Instruct-2509-UD-Q4_K_XL.gguf new file mode 100644 index 0000000..f539ff2 --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975d509d9677854c8680a3414f2e7fd8d42b2e957230889675d56e43477c1642 +size 5135938816 diff --git a/Apertus-8B-Instruct-2509-UD-Q5_K_XL.gguf b/Apertus-8B-Instruct-2509-UD-Q5_K_XL.gguf new file mode 100644 index 0000000..26d5b1a --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-Q5_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e517c010ceb9ba39dad41f9082c3394f7decc63dd4c86bb0691aa9cfa9cf17 +size 5823968512 diff --git a/Apertus-8B-Instruct-2509-UD-Q6_K_XL.gguf b/Apertus-8B-Instruct-2509-UD-Q6_K_XL.gguf new file mode 100644 index 0000000..9aa4cff --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-Q6_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79057e86304fb3676e45d286bfe867e138994d591547ad9bebce7662277c1bdd +size 7390082304 diff --git a/Apertus-8B-Instruct-2509-UD-Q8_K_XL.gguf b/Apertus-8B-Instruct-2509-UD-Q8_K_XL.gguf new file mode 100644 index 0000000..3a79ded --- /dev/null +++ b/Apertus-8B-Instruct-2509-UD-Q8_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1b6a4ce380747749a0427422b7bea89350933efae139fc06f2411eaa772cff +size 10621891840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ee7fcc1 --- /dev/null +++ b/README.md @@ -0,0 +1,186 @@ +--- +license: apache-2.0 +base_model: +- swiss-ai/Apertus-8B-Instruct-2509 +pipeline_tag: text-generation +library_name: transformers +tags: + - multilingual + - compliant + - swiss-ai + - apertus + +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. " +extra_gated_fields: + Your Name: text + Country: country + Affiliation: text + geo: ip_location + By clicking Submit below I accept the terms of use: checkbox +extra_gated_button_content: Submit +--- + +# Apertus + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6639f08490b7db8dcbf1a2aa/YKux3SpTciL4O60L3Ol-6.jpeg) + +## Table of Contents + +1. [Model Summary](#model-summary) +2. [How to use](#how-to-use) +3. [Evaluation](#evaluation) +4. [Training](#training) +5. [Limitations](#limitations) +6. [Legal Aspects](#legal-aspects) + +## Model Summary + +Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models. +The model supports over 1000 languages and long context, it uses only fully compliant and open training data, and achieves comparable performance to models trained behind closed doors. + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/654baf61d625e083383dfd00/gKDv_6dpIpvmgyquenbXt.png) + +The model is a decoder-only transformer, pretrained on 15T tokens with a staged curriculum of web, code and math data. The model uses a new xIELU activation function and is trained from scratch with the AdEMAMix optimizer. Post-training included supervised fine-tuning and alignment via QRPO. + +### Key features +- **Fully open model**: open weights + open data + full training details including all data and training recipes +- **Massively Multilingual**: 1811 natively supported languages +- **Compliant** Apertus is trained while respecting opt-out consent of data owners (even retrospectivey), and avoiding memorization of training data + +For more details refer to our [technical report](https://arxiv.org/abs/2509.14233) + +## How to use + +The modeling code for Apertus is available in transformers `v4.56.0` and later, so make sure to upgrade your transformers version. You can also load the model with the latest `vLLM` which uses transformers as a backend. +```bash +pip install -U transformers +``` + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "swiss-ai/Apertus-8B-Instruct-2509" +device = "cuda" # for GPU usage or "cpu" for CPU usage + +# load the tokenizer and the model +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, +).to(device) + +# prepare the model input +prompt = "Give me a brief explanation of gravity in simple terms." +messages_think = [ + {"role": "user", "content": prompt} +] + +text = tokenizer.apply_chat_template( + messages_think, + tokenize=False, + add_generation_prompt=True, +) +model_inputs = tokenizer([text], return_tensors="pt", add_special_tokens=False).to(model.device) + +# Generate the output +generated_ids = model.generate(**model_inputs, max_new_tokens=32768) + +# Get and decode the output +output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :] +print(tokenizer.decode(output_ids, skip_special_tokens=True)) +``` + +>[!TIP] +> We recommend setting `temperature=0.8` and `top_p=0.9` in the sampling parameters. + +### Long context processing + +Apertus by default supports a context length up to 65,536 tokens. + +### Agentic Usage + +Apertus supports tool use + +### Deployment + +Deployment of the models is directly supported by the newest versions of [Transformers](https://github.com/huggingface/transformers), [vLLM](https://github.com/vllm-project/vllm), [SGLang](https://github.com/sgl-project/sglang), and also for running on-device with [MLX](https://github.com/ml-explore/mlx-lm), + +## Evaluation + +**Pretraining Evaluation:** Performance (%) of Apertus models on *general language understanding* tasks (higher is better) compared to other pretrained models. + +| **Model** | **Avg** | **ARC** | **HellaSwag** | **WinoGrande** | **XNLI** | **XCOPA** | **PIQA** | +| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | +| **Fully Open Models** | | | | | | | | +| **Apertus-8B** | 65.8 | 72.7 | 59.8 | 70.6 | 45.2 | 66.5 | 79.8 | +| **Apertus-70B** | 67.5 | 70.6 | 64.0 | 73.3 | 45.3 | 69.8 | 81.9 | +| OLMo2-7B | 64.0 | 72.9 | 60.4 | 74.5 | 40.4 | 55.2 | 80.9 | +| OLMo2-32B | 67.7 | 76.2 | 66.7 | 78.6 | 42.9 | 60.1 | 82.1 | +| EuroLLM-1.7B | 54.8 | 57.2 | 44.9 | 58.1 | 40.7 | 55.7 | 72.4 | +| EuroLLM-9B | 62.8 | 67.9 | 57.9 | 68.8 | 41.5 | 61.1 | 79.6 | +| SmolLM2-1.7B | 58.5 | 66.1 | 52.4 | 65.6 | 37.6 | 52.3 | 77.0 | +| SmolLM3-3B | 61.6 | 68.6 | 56.4 | 68.1 | 40.5 | 58.2 | 77.7 | +| Poro-34B | 61.7 | 65.7 | 57.9 | 70.6 | 41.6 | 56.0 | 78.5 | +| **Open-Weight Models** | | | | | | | | +| Llama3.1-8B | 65.4 | 71.6 | 60.0 | 73.4 | 45.3 | 61.8 | 80.1 | +| Llama3.1-70B | 67.3 | 74.4 | 56.5 | 79.4 | 44.3 | 66.7 | 82.3 | +| Qwen2.5-7B | 64.4 | 69.6 | 60.1 | 72.8 | 43.3 | 61.7 | 78.7 | +| Qwen2.5-72B | 69.8 | 76.2 | 67.5 | 78.0 | 46.9 | 68.2 | 82.0 | +| Qwen3-32B | 67.8 | 75.6 | 64.0 | 73.8 | 44.4 | 67.9 | 80.9 | +| Llama4-Scout-16x17B | 67.9 | 74.7 | 66.8 | 73.2 | 43.5 | 67.7 | 81.2 | +| GPT-OSS-20B | 58.1 | 67.0 | 41.5 | 66.5 | 37.4 | 60.4 | 75.6 | + +Many additional benchmark evaluations, for pretraining and posttraining phases, multilingual evaluations in around hundred languages, and long context evaluations are provided in Section 5 of the [Apertus_Tech_Report.pdf](https://github.com/swiss-ai/apertus-tech-report/blob/main/Apertus_Tech_Report.pdf) + +## Training + +### Model + +- **Architecture:** Transformer decoder +- **Pretraining tokens:** 15T +- **Precision:** bfloat16 + +### Software & hardware + +- **GPUs:** 4096 GH200 +- **Training Framework:** [Megatron-LM](https://github.com/swiss-ai/Megatron-LM) +- ... + +### Open resources +All elements used in the training process are made openly available +- **Training data reconstruction scripts:** [github.com/swiss-ai/pretrain-data](https://github.com/swiss-ai/pretrain-data) +- The training intermediate checkpoints are available on the different branches of this same repository + + +## Limitations + +Apertus can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content. + + +## Legal Aspects + +#### EU AI Act Transparency Documentation and Code of Practice +- [Apertus_EU_Public_Summary.pdf](https://huggingface.co/swiss-ai/Apertus-70B-2509/blob/main/Apertus_EU_Public_Summary.pdf) +- [Apertus_EU_Code_of_Practice.pdf](https://huggingface.co/swiss-ai/Apertus-70B-2509/blob/main/Apertus_EU_Code_of_Practice.pdf) + +#### Data Protection and Copyright Requests +For removal requests of personally identifiable information (PII) or of copyrighted content, please contact the respective dataset owners or us directly +- llm-privacy-requests@swiss-ai.org +- llm-copyright-requests@swiss-ai.org + +#### Output Filter for PII +- Currently no output filter is provided. +- Please check this site regularly for an output filter that can be used on top of the Apertus LLM. The filter reflects data protection deletion requests which have been addressed to us 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 this site every six months. + +## Contact +To contact us, please send an email to +llm-requests@swiss-ai.org + +## Citation +```bash +@misc{swissai2025apertus, + title={{Apertus: Democratizing Open and Compliant LLMs for Global Language Environments}}, + author={Alejandro Hernández-Cano and Alexander Hägele and Allen Hao Huang and Angelika Romanou and Antoni-Joan Solergibert and Barna Pasztor and Bettina Messmer and Dhia Garbaya and Eduard Frank Ďurech and Ido Hakimi and Juan García Giraldo and Mete Ismayilzada and Negar Foroutan and Skander Moalla and Tiancheng Chen and Vinko Sabolčec and Yixuan Xu and Michael Aerni and Badr AlKhamissi and Ines Altemir Marinas and Mohammad Hossein Amani and Matin Ansaripour and Ilia Badanin and Harold Benoit and Emanuela Boros and Nicholas Browning and Fabian Bösch and Maximilian Böther and Niklas Canova and Camille Challier and Clement Charmillot and Jonathan Coles and Jan Deriu and Arnout Devos and Lukas Drescher and Daniil Dzenhaliou and Maud Ehrmann and Dongyang Fan and Simin Fan and Silin Gao and Miguel Gila and María Grandury and Diba Hashemi and Alexander Hoyle and Jiaming Jiang and Mark Klein and Andrei Kucharavy and Anastasiia Kucherenko and Frederike Lübeck and Roman Machacek and Theofilos Manitaras and Andreas Marfurt and Kyle Matoba and Simon Matrenok and Henrique Mendoncça and Fawzi Roberto Mohamed and Syrielle Montariol and Luca Mouchel and Sven Najem-Meyer and Jingwei Ni and Gennaro Oliva and Matteo Pagliardini and Elia Palme and Andrei Panferov and Léo Paoletti and Marco Passerini and Ivan Pavlov and Auguste Poiroux and Kaustubh Ponkshe and Nathan Ranchin and Javi Rando and Mathieu Sauser and Jakhongir Saydaliev and Muhammad Ali Sayfiddinov and Marian Schneider and Stefano Schuppli and Marco Scialanga and Andrei Semenov and Kumar Shridhar and Raghav Singhal and Anna Sotnikova and Alexander Sternfeld and Ayush Kumar Tarun and Paul Teiletche and Jannis Vamvas and Xiaozhe Yao and Hao Zhao Alexander Ilic and Ana Klimovic and Andreas Krause and Caglar Gulcehre and David Rosenthal and Elliott Ash and Florian Tramèr and Joost VandeVondele and Livio Veraldi and Martin Rajman and Thomas Schulthess and Torsten Hoefler and Antoine Bosselut and Martin Jaggi and Imanol Schlag}, + year={2025}, + howpublished={\url{https://arxiv.org/abs/2509.14233}} +} +``` \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/imatrix_unsloth.gguf_file b/imatrix_unsloth.gguf_file new file mode 100644 index 0000000..b5e9718 --- /dev/null +++ b/imatrix_unsloth.gguf_file @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122585fdf7656b25f01e41488cea2fb934a6222521f9b790bdd4205e98af99ae +size 5403520