[BUG] qwen-vl大概什么能支持llama.cpp转换，或者有没有工具转gguf或ggml格式
fan-chao opened this issue · 1 comments
同样想了解这个问题。我在转换中碰到了问题：
Loading model: Qwen-VL-Chat-Int4
gguf: This GGUF file is for Little Endian only
Set model parameters
Set model tokenizer
gguf: Adding 151387 merge(s).
gguf: Setting special token type bos to 151643
gguf: Setting special token type eos to 151643
gguf: Setting special token type unk to 151643
Exporting model to 'converted.bin'
gguf: loading model part 'model-00001-of-00005.safetensors'
gguf: loading model part 'model-00002-of-00005.safetensors'
gguf: loading model part 'model-00003-of-00005.safetensors'
gguf: loading model part 'model-00004-of-00005.safetensors'
gguf: loading model part 'model-00005-of-00005.safetensors'
blk.0.attn_qkv.bias, n_dims = 1, torch.float16 --> float32
Can not map tensor 'transformer.h.0.attn.c_attn.g_idx'