Instructions to use codllm/codllm-base-deploy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

codllm-base-deploy / NOTICE

lucasmortensen

Apply CC BY 4.0 to codLLM contributions with citation and upstream notices

992a7ea verified 3 days ago

Raw History Blame Contribute Delete

1.07 kB

codLLM
Copyright (c) 2026 Elias Dahl Lunøe & Lucas E. Bülow Mortensen

Project: https://github.com/murrodroid/codllm
Models: https://huggingface.co/codllm

codLLM software is licensed under Apache-2.0. Project-authored prose,
documentation, the bachelor's thesis, and codLLM model contributions are
licensed under CC BY 4.0, as scoped in LICENSING.md. Third-party
materials retain their own terms.

The deployment model modifies Google's google/flan-t5-base through
codLLM training. FLAN-T5-base is distributed under Apache-2.0:
https://huggingface.co/google/flan-t5-base
The upstream Apache license and applicable notices must be retained.

Earlier codLLM software was distributed under MIT; its original notice
is preserved in LICENSE-MIT-legacy. Earlier model revisions retain
their original license grants. This update does not revoke those grants.

Please credit Lucas E. B. Mortensen and Elias Dahl Lunøe and cite the
thesis when using codLLM in research. CITATION.cff provides the preferred
citation. This request does not add conditions to the standard licenses.

	codLLM
	Copyright (c) 2026 Elias Dahl Lunøe & Lucas E. Bülow Mortensen

	Project: https://github.com/murrodroid/codllm
	Models: https://huggingface.co/codllm

	codLLM software is licensed under Apache-2.0. Project-authored prose,
	documentation, the bachelor's thesis, and codLLM model contributions are
	licensed under CC BY 4.0, as scoped in LICENSING.md. Third-party
	materials retain their own terms.

	The deployment model modifies Google's google/flan-t5-base through
	codLLM training. FLAN-T5-base is distributed under Apache-2.0:
	https://huggingface.co/google/flan-t5-base
	The upstream Apache license and applicable notices must be retained.

	Earlier codLLM software was distributed under MIT; its original notice
	is preserved in LICENSE-MIT-legacy. Earlier model revisions retain
	their original license grants. This update does not revoke those grants.

	Please credit Lucas E. B. Mortensen and Elias Dahl Lunøe and cite the
	thesis when using codLLM in research. CITATION.cff provides the preferred
	citation. This request does not add conditions to the standard licenses.