Instructions to use SEN-AGI/Lily-1.0-10M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SEN-AGI/Lily-1.0-10M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SEN-AGI/Lily-1.0-10M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SEN-AGI/Lily-1.0-10M") model = AutoModelForCausalLM.from_pretrained("SEN-AGI/Lily-1.0-10M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SEN-AGI/Lily-1.0-10M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SEN-AGI/Lily-1.0-10M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SEN-AGI/Lily-1.0-10M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SEN-AGI/Lily-1.0-10M
- SGLang
How to use SEN-AGI/Lily-1.0-10M 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 "SEN-AGI/Lily-1.0-10M" \ --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": "SEN-AGI/Lily-1.0-10M", "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 "SEN-AGI/Lily-1.0-10M" \ --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": "SEN-AGI/Lily-1.0-10M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SEN-AGI/Lily-1.0-10M with Docker Model Runner:
docker model run hf.co/SEN-AGI/Lily-1.0-10M
Lily-1.0-10M
An optimized, ultra-lightweight language model variant based on the Llama architecture. Highly efficient and perfect for edge-device integration or local rapid experimentation.
Model Summary
- Developed by: SENAGI
- Model Size: 10.3M parameters
- Tensor Type: F32 / Safetensors
- License: Apache 2.0
- Base Architecture: Llama-based variant
Intended Uses & Performance
Ideal for highly resource-constrained environments, research prototypes, tokenization mechanics training, and character-level language generation tasks.
- Downloads last month
- 269