| 0.00.362.534 W load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect | |
| 0.10.078.480 I cmn init: llama threadpool init, n_threads = 16 | |
| 0.10.103.754 W load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks | |
| 0.10.103.757 W load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024 | |
| 0.10.103.758 W load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842 | |
| 0.10.849.878 I mtmd_cli_context: chat template example: | |
| [unused9]系统：You are a helpful assistant[unused10][unused9]用户：Hello[unused10][unused9]助手：Hi there[unused10][unused9]用户：How are you?[unused10][unused9]助手： | |
| 0.10.849.883 I main: loading model: ./openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf | |
| 0.10.849.982 W WARN: This is an experimental CLI for testing multimodal capability. | |
| 0.10.849.983 W For normal use cases, please use the standard llama-cli | |
| 0.11.297.560 I encoding mtmd batch, n_chunks = 1 (done = 1, total = 3) | |
| 4.00.711.965 I mtmd batch encoding done in 229415 ms | |
| The | |