Text Generation
Transformers
Safetensors
t5
text2text-generation
icd
historical-demography
digital-humanities
multi-label
text-generation-inference
Instructions to use codllm/codllm-base-deploy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codllm/codllm-base-deploy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="codllm/codllm-base-deploy")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("codllm/codllm-base-deploy") model = AutoModelForSeq2SeqLM.from_pretrained("codllm/codllm-base-deploy", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use codllm/codllm-base-deploy with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "codllm/codllm-base-deploy" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codllm/codllm-base-deploy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/codllm/codllm-base-deploy
- SGLang
How to use codllm/codllm-base-deploy with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "codllm/codllm-base-deploy" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codllm/codllm-base-deploy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "codllm/codllm-base-deploy" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codllm/codllm-base-deploy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use codllm/codllm-base-deploy with Docker Model Runner:
docker model run hf.co/codllm/codllm-base-deploy
|
Download LICENSING.md from codllm/codllm-base-deploy: direct link, hf CLI and curl.
- Browser
- Download file 4.72 kB
-
https://huggingface.co/codllm/codllm-base-deploy/resolve/main/LICENSING.md
- Command line
-
hf download hf://codllm/codllm-base-deploy/LICENSING.md
-
curl -L -o LICENSING.md https://huggingface.co/codllm/codllm-base-deploy/resolve/main/LICENSING.md
4.72 kB
| # Licensing and citation | |
| codLLM permits commercial and non-commercial use, modification, and redistribution under standard licenses. | |
| The license depends on the material; these are not alternative licenses for the same material. | |
| | Material | License | | |
| |---|---| | |
| | Project software, scripts, tests, configuration, and code examples, including code in documentation | [Apache-2.0](./LICENSE-APACHE) | | |
| | Project-authored prose, documentation, figures, organization/model cards, and the authors' contributions to `codLLM_Thesis.pdf` | [CC BY 4.0](./LICENSE) | | |
| | codLLM model contributions released under this policy | [CC BY 4.0](./LICENSE), with upstream model terms and notices retained | | |
| | Third-party datasets, ICD10h masterlists/reference materials, dependencies, and attributed third-party content | Their respective terms; not relicensed by codLLM | | |
| Unless a file or release explicitly states otherwise, this scope applies to project-owned materials from this update | |
| onward. It does not grant rights that the authors do not hold. Third-party quotations, figures, and other attributed | |
| material in the thesis are excluded from the CC BY grant unless their own notices say otherwise. Raw archival datasets | |
| remain subject to their data-use agreements and are not distributed under either project license. | |
| The license texts are authoritative. [NOTICE](./NOTICE) records authorship and upstream attribution; | |
| [CITATION.cff](./CITATION.cff) provides the preferred citation. | |
| ## Attribution and citation | |
| **Please credit Lucas E. B. Mortensen and Elias Dahl Lunøe when using codLLM, and cite the thesis in research publications.** | |
| Also identify the model name and revision used, so that results can be traced to a specific checkpoint. | |
| > Mortensen, Lucas E. B., and Elias Dahl Lunøe. 2026. *Automated Historical Cause-of-Death Coding Using Fine-Tuned | |
| > Language Models*. Bachelor's thesis, DTU Compute, Technical University of Denmark. | |
| [Read the thesis](https://huggingface.co/spaces/codllm/README/resolve/main/codLLM_Thesis.pdf). | |
| When publicly sharing CC BY material or adaptations, give appropriate credit, link to the material and license, | |
| retain supplied notices, and indicate changes as required by CC BY 4.0. For example: | |
| > Based on codLLM by Lucas E. B. Mortensen and Elias Dahl Lunøe (2026), | |
| > https://huggingface.co/codllm. Licensed under CC BY 4.0: https://creativecommons.org/licenses/by/4.0/. | |
| > Changes: [describe your changes, or state that none were made]. | |
| For a model redistribution, link to the specific model and retain its upstream notices as well. | |
| For software redistribution, follow Apache-2.0's license, notice, attribution, and change-marking requirements. | |
| The research citation request is not an added license condition. These standard licenses do not impose a universal | |
| citation obligation merely for running the model, operating a service, or publishing outputs that do not themselves | |
| share licensed material. There are no additional non-commercial, field-of-use, or share-alike restrictions. | |
| ## Model provenance and prior releases | |
| `codllm/codllm-base-deploy` is derived from Google's | |
| [FLAN-T5-base](https://huggingface.co/google/flan-t5-base), distributed under Apache-2.0. | |
| The CC BY declaration covers the codLLM contributions; it does not replace Google's license or attribution. | |
| Model releases must carry the applicable upstream license text and notices alongside the codLLM license and citation. | |
| Earlier software versions were released under MIT. The original notice is preserved in | |
| [LICENSES/MIT-legacy.txt](./LICENSE-MIT-legacy) and must be retained for incorporated MIT material. | |
| Earlier model revisions were released under Apache-2.0. This policy does not revoke permissions already granted: | |
| recipients can continue to use those earlier releases under their original terms, including where the same material | |
| is also offered under the new policy. No retroactive attribution or citation requirement is asserted. | |
| Future publication models must identify their actual upstream model, license scope, authors, and associated paper. | |
| Do not use a planned publication as if it were an existing citation. | |
| ## Official license references | |
| - [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0) | |
| - [CC BY 4.0 legal code](https://creativecommons.org/licenses/by/4.0/legalcode.en) | |
| - [Creative Commons attribution guidance](https://creativecommons.org/faq/#do-i-always-have-to-attribute-the-creator-of-the-licensed-material) | |
| Creative Commons [recommends software-specific licenses for code](https://creativecommons.org/faq/#can-i-apply-a-creative-commons-license-to-software), | |
| which is why codLLM software uses Apache-2.0 and its other project-owned materials use CC BY 4.0. | |