Views
No views yet
1# llama.cpp
2./main -m vet-qwen3b-v3-dapt-q8_0.gguf -p "..." -n 512
3
4# llama-cpp-python
5from llama_cpp import Llama
6llm = Llama(model_path="vet-qwen3b-v3-dapt-q8_0.gguf", n_ctx=4096)vet-qwen3b-v3-dapt-q8_0.gguf — 量化权重（3.1 GB）