model.save_pretrained_gguf("model", tokenizer, quantization_method = "q4_k_m") File "J:\Test\Llama3-Fine-Tuning-Windows\unsloth\unsloth\save.py", line 1360, in unsloth_save_pretrained_gguf file_location = save_to_gguf(model_type, new_save_directory, quantization_method, first_conversion, makefile) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "J:\Test\Llama3-Fine-Tuning-Windows\unsloth\unsloth\save.py", line 967, in save_to_gguf raise RuntimeError( RuntimeError: Unsloth: Quantization failed for ./model-unsloth.F16.gguf You might have to compile llama.cpp yourself, then run this again. You do not need to close this Python program. Run the following commands in a new terminal: You must run this in the same folder as you're saving your model. git clone github.com/ggerganov/llama.cpp cd llama.cpp && make clean && LLAMA_CUDA=1 make all -j Once that's done, redo the quantization. 请教下,这个是什么错误,llama.cpp已经手动编译过了
@WumayahaКүн бұрын
有没有办法使用克隆自己的音色来合成语音🧐
@AIDiscovery2045Күн бұрын
目前还没有,要等开放训练功能
@user-tv6sj9jt7lКүн бұрын
大佬,最后一步,推理模型,提示施工中请静候佳音,怎么解决?
@AIDiscovery2045Күн бұрын
施工中不是推理,还未开放的RVC,推理功能在下面一行
@XiaojianQiu2 күн бұрын
请问保存成GGUF的时候报错怎么办? RuntimeError "Unsloth: first_conversion can only be one of ['f16', 'bf16', 'f32', 'q8_0'] and not {first_conversion}." RuntimeError: Unsloth: first_conversion can only be one of ['f16', 'bf16', 'f32', 'q8_0'] and not f16.
@AIDiscovery20452 күн бұрын
可能需要手动转换了;这个错误提示:第一次保存为f16时应该就没成功
@shilohjenna21302 күн бұрын
大佬第一步切片的时候报错File "C:\Program Files (x86)\AI\GPT-SoVITS-beta0217fix2\GPT-SoVITS-beta0217fix2\tools\slice_audio.py", line 6, in <module> from my_utils import load_audio ModuleNotFoundError: No module named 'my_utils'怎么解决呀
(venv) D:\AI_Soft\facefusion>pip install -r requirements.txt Fatal error in launcher: Unable to create process using '"D:\AI_Soft\facefusion\facefusion-master\venv\Scripts\python.exe" "D:\AI_Soft\facefusion\venv\Scripts\pip.exe" install -r requirements.txt': ??????????? 请教这个怎么解决?
@AIDiscovery20453 күн бұрын
关于roop网页版,可以看最新的教程,这期是很早已前的版本了,频道里搜索facefusion
@user-rm8td8el6r4 күн бұрын
大佬 这个可以讲下Mac的码?
@user-bw5dp8dq1h4 күн бұрын
老师,出现这个问题怎么解决:Frame processor clear_reality_x4 could not be loaded
@AIDiscovery20454 күн бұрын
重新下载这个模型文件
@user-bw5dp8dq1h3 күн бұрын
@@AIDiscovery2045 重新下载了,也放进去了,还是显示这个
@user-bw5dp8dq1h4 күн бұрын
老师,如果想把 facefusion 从电脑上完全移除,需要怎么做。我的电脑是 m1 的 macbook air
@AIDiscovery20454 күн бұрын
删除facefusion文件夹即可
@user-bw5dp8dq1h3 күн бұрын
@@AIDiscovery2045 好的,谢谢
@user-wn6eq5tk9g4 күн бұрын
大佬,mac部署时,最后一步运行pyton.webui.py时显示readtimeout是怎么回事
@AIDiscovery20454 күн бұрын
换梯子IP
@JM_Animation774 күн бұрын
“ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.”怎么设置?
@mmmm-sj4jh4 күн бұрын
大佬点start出现这行怎么办[FACEFUSION.PROCESSORS.FRAME.MODULES.FACE_SWAPPER] Select a file or directory for output path!
Extracting frames with a resolution of 720x1280 and 30.0 frames per second Extracting frames failed ConnectionResetError: [WinError 10054] 远程主机强迫关闭了一个现有的连接。 老师这是怎么回事呢?
@AIDiscovery20455 күн бұрын
梯子的原因,不影响使用
@user-ik9oz2nb3p4 күн бұрын
@@AIDiscovery2045 老师,为什么我一转换视频就出错呢?
@AIDiscovery20454 күн бұрын
@@user-ik9oz2nb3p 把命令窗口的出错信息发来看看;
@AIDiscovery20455 күн бұрын
google drive文件超过限额解决办法:右键->整理->添加星标;左侧点【已加星标】、右键复制,会生成副本,通过副本下载绕过限额
@AIDiscovery20455 күн бұрын
google drive文件超过限额解决办法:右键->整理->添加星标;左侧点【已加星标】、右键复制,会生成副本,通过副本下载绕过限额