Instructions to use logitshq/Logits-Sigma-1-Duo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use logitshq/Logits-Sigma-1-Duo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="logitshq/Logits-Sigma-1-Duo")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("logitshq/Logits-Sigma-1-Duo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download code/requirements.lock from logitshq/Logits-Sigma-1-Duo: direct link, hf CLI and curl.
- Browser
- Download file 1.66 kB
-
https://huggingface.co/logitshq/Logits-Sigma-1-Duo/resolve/main/code/requirements.lock
- Command line
-
hf download hf://logitshq/Logits-Sigma-1-Duo/code/requirements.lock
-
curl -L -o requirements.lock https://huggingface.co/logitshq/Logits-Sigma-1-Duo/resolve/main/code/requirements.lock
1.66 kB
| # The H200 box's serving venv (~/ldm/.venv-qwen, Python 3.12.3, torch 2.15.0+cu132, driver 580.126.16), listed with | |
| # importlib.metadata on 2026-11-07 (uv venv: pip freeze prints nothing). decision-index is installed from the kit (-e di). | |
| accelerate==1.15.0 | |
| aiohappyeyeballs==2.7.1 | |
| aiohttp==3.14.5 | |
| aiosignal==1.4.0 | |
| annotated-doc==0.0.5 | |
| anyio==4.16.0 | |
| attrs==26.1.0 | |
| click==8.5.0 | |
| cuda-bindings==13.5.0 | |
| cuda-pathfinder==1.8.5 | |
| cuda-toolkit==13.2.2 | |
| datasets==5.1.0 | |
| dill==0.4.1 | |
| einops==0.8.2 | |
| filelock==4.2.9 | |
| fla-core==0.6.0 | |
| flash-linear-attention==0.6.0 | |
| frozenlist==1.8.0 | |
| fsspec==2026.7.0 | |
| h11==0.16.0 | |
| hf-xet==1.8.0 | |
| httpcore2==2.16.0 | |
| httpx2==2.16.0 | |
| huggingface_hub==2.4.0 | |
| idna==3.20 | |
| Jinja2==3.1.6 | |
| markdown-it-py==4.2.0 | |
| MarkupSafe==3.0.4 | |
| mdurl==0.1.2 | |
| mpmath==1.3.0 | |
| multidict==7.2.1 | |
| multiprocess==0.70.19 | |
| networkx==3.7 | |
| ninja==1.13.2 | |
| numpy==2.5.4 | |
| nvidia-cublas==13.4.1.3 | |
| nvidia-cuda-cccl==13.3.5.0.6 | |
| nvidia-cuda-cupti==13.2.86 | |
| nvidia-cuda-nvrtc==13.2.86 | |
| nvidia-cuda-runtime==13.2.86 | |
| nvidia-cudnn-cu13==9.26.0.51 | |
| nvidia-cufft==12.2.0.57 | |
| nvidia-cufile==1.17.1.22 | |
| nvidia-cusolver==12.2.0.11 | |
| nvidia-cusparse==12.7.10.12 | |
| nvidia-cusparselt-cu13==0.8.1 | |
| nvidia-nccl-cu13==2.30.7 | |
| nvidia-nvjitlink==13.5.37 | |
| nvidia-nvshmem-cu13==3.7.2 | |
| nvidia-nvtx==13.2.86 | |
| packaging==26.3 | |
| pandas==3.1.1 | |
| peft==0.21.2 | |
| propcache==0.5.4 | |
| psutil==7.2.2 | |
| pyarrow==26.0.1 | |
| Pygments==2.21.0 | |
| python-dateutil==4.0.0 | |
| PyYAML==6.0.3 | |
| regex==2026.9.29 | |
| rich==15.0.0 | |
| safetensors==0.8.0 | |
| setuptools==84.2.1 | |
| shellingham==1.5.4 | |
| sympy==1.14.0 | |
| tokenizers==0.23.3 | |
| torch==2.15.0 | |
| tqdm==4.70.1 | |
| transformers==5.22.1 | |
| triton==3.9.0 | |
| truststore==0.10.5 | |
| typer==0.27.3 | |
| typing_extensions==4.16.0 | |
| tzdata==2026.6 | |
| xxhash==4.0.2 | |
| yarl==1.25.1 | |