Instructions to use llmware/dragon-deci-7b-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llmware/dragon-deci-7b-v0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="llmware/dragon-deci-7b-v0", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("llmware/dragon-deci-7b-v0", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use llmware/dragon-deci-7b-v0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "llmware/dragon-deci-7b-v0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llmware/dragon-deci-7b-v0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/llmware/dragon-deci-7b-v0
- SGLang
How to use llmware/dragon-deci-7b-v0 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 "llmware/dragon-deci-7b-v0" \ --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": "llmware/dragon-deci-7b-v0", "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 "llmware/dragon-deci-7b-v0" \ --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": "llmware/dragon-deci-7b-v0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use llmware/dragon-deci-7b-v0 with Docker Model Runner:
docker model run hf.co/llmware/dragon-deci-7b-v0
Set model_type
Please add model_type to the config as DeciLM has now done. Unfortunately this changes the model type from deci_lm to deci which will break the 0.6.0 implementation of the model in AutoGPTQ, I made a PR there to change this but that means either one of those will not work there, so for future I would support the explicitly set "model_type": "deci".
Loading with AutoGPTQ directly will require manually setting it depending on the version.
Great feedback - agree 100% - thanks for highlighting this. I have updated the config.json file to include "model_type": "deci" - keep me posted and let me know if this fixes the issue with AutoGPTQ. I had similar issues with GGUF and fixing was on my to-do list.