DaMorph
Collection
DaMorph is a collection of experimental models developed to explore the impact of morphological segmentation on Danish NLP. • 8 items • Updated
Text Generation
Transformers
Safetensors
gpt2
Danish
Morphological Tokenization
CerebrasGPT
text-generation-inference
How to use from
SGLangUse 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 "RyeAI/DA-MORPH-CEREBRAS" \
--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": "RyeAI/DA-MORPH-CEREBRAS",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
_______ ___ .___ ___. ______ .______ .______ __ __
| \ / \ | \/ | / __ \ | _ \ | _ \ | | | |
| .--. | / ^ \ | \ / | | | | | | |_) | | |_) | | |__| |
| | | | / /_\ \ | |\/| | | | | | | / | ___/ | __ |
| '--' | / _____ \ | | | | | `--' | | |\ \----.| | | | | |
|_______/ /__/ \__\ |__| |__| \______/ | _| `._____|| _| |__| |__|
DA-MORPH-CEREBRAS
This experimental model, built on the CerebrasGPT-111M architecture, uses a custom morphological tokenizer specifically designed for Danish. It explores the impact of morphology-aware tokenization on Danish text generation and understanding.
- Downloads last month
- 2
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "RyeAI/DA-MORPH-CEREBRAS" \ --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": "RyeAI/DA-MORPH-CEREBRAS", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'