Open hgsw opened 2 weeks ago
使用llama.cpp/convert_hf_to_gguf.py模型格式转换失败,7B的这个多模态模型是不允许转换吗,转换指令如下: python convert_hf_to_gguf.py /data/houshiwei/qwen2_model/Qwen/Qwen2-VL-7B-Instruct --outfile /data/houshiwei/gguf_model
报错信息如下: (gguf_env) fxzx@fxzx-Z790-EAGLE-AX:/data/houshiwei/llama.cpp$ python convert_hf_to_gguf.py /data/houshiwei/qwen2_model/Qwen/Qwen2-VL-7B-Instruct --outfile /data/houshiwei/gguf_model INFO:hf-to-gguf:Loading model: Qwen2-VL-7B-Instruct ERROR:hf-to-gguf:Model Qwen2VLForConditionalGeneration is not supported (gguf_env) fxzx@fxzx-Z790-EAGLE-AX:/data/houshiwei/llama.cpp$
现在你转换成功了吗?
没转成功,貌似就是不支持的
使用llama.cpp/convert_hf_to_gguf.py模型格式转换失败,7B的这个多模态模型是不允许转换吗,转换指令如下: python convert_hf_to_gguf.py /data/houshiwei/qwen2_model/Qwen/Qwen2-VL-7B-Instruct --outfile /data/houshiwei/gguf_model
报错信息如下: (gguf_env) fxzx@fxzx-Z790-EAGLE-AX:/data/houshiwei/llama.cpp$ python convert_hf_to_gguf.py /data/houshiwei/qwen2_model/Qwen/Qwen2-VL-7B-Instruct --outfile /data/houshiwei/gguf_model INFO:hf-to-gguf:Loading model: Qwen2-VL-7B-Instruct ERROR:hf-to-gguf:Model Qwen2VLForConditionalGeneration is not supported (gguf_env) fxzx@fxzx-Z790-EAGLE-AX:/data/houshiwei/llama.cpp$