swiftLLM
swiftLLM copied to clipboard
Support for the Llama3.2-1B
Basic Test:
- offline mode:
python3 examples/offline.py --model-path ./models/Llama-3.2-1B - online mode:
python3 examples/online.py --model-path ./models/Llama-3.2-1B - api_server:
python3 swiftllm/server/api_server.py --model-path ./models/Llama-3.2-1B/ --host 0.0.0.0 --port 8082
The 3B model is not supported due to its hidden layer dimension of 3072