Text Generation
Transformers
Safetensors
English
deci
Deci AI
DeciLM
custom_code
Eval Results (legacy)
Instructions to use Deci/DeciLM-6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Deci/DeciLM-6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Deci/DeciLM-6b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Deci/DeciLM-6b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Deci/DeciLM-6b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Deci/DeciLM-6b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Deci/DeciLM-6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Deci/DeciLM-6b
- SGLang
How to use Deci/DeciLM-6b 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 "Deci/DeciLM-6b" \ --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": "Deci/DeciLM-6b", "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 "Deci/DeciLM-6b" \ --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": "Deci/DeciLM-6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Deci/DeciLM-6b with Docker Model Runner:
docker model run hf.co/Deci/DeciLM-6b
Is this a derivative model?
#3
by Said2k - opened
"Deci.AI's DeciLM, derivative of the LLAMA 2 model, offers a vast suite of AI tools and code. This license balances user flexibility with Deci.AI's proprietary rights, aiming for collaborative growth in AI."
It seems that your license is saying that DeciLM is a derivative, is this a mistake?
Is DeciLM a fine-tuned version of llama 2 model?
Hey @Said2k ,
DeciLM has a different model architecture that was created by Deci. We used some of Llama2 weights to initialize training therefore we are a derivative of Llama2.
itay-levy changed discussion status to closed