Bios

RuntimeError: unexpected EOF, expected 6387653 more bytes. The file might be corrupted. 在将三个文档都放入到bert_pretain文件后，为什么会在load_data结束后，报文件损坏错误

I can‘t find BatchedInferencePipeline.

4

faster_whisper == 1.0.3 from faster_whisper import WhisperModel, BatchedInferencePipeline model = WhisperModel("medium", device="cuda", compute_type="float16") batched_model = BatchedInferencePipeline(model=model) segments, info = batched_model.transcribe("audio.wav", batch_size=16) for segment in segments: print("[%.2fs -> %.2fs] %s" %...

**问题** 将词云图的html保存为png，运行成功但是png文件都是空 ,什么字也没有  **运行环境（系统环境及 pyecharts 版本）** pyecharts 2.0.6 **代码及截图** def test_make_jieba_word(self): txt = """例如，在上述代码中，length变量被初始化为float('inf')，目的是为了后续在寻找最小覆盖子串的过程中，能够将首次找到的有效子串长度与之比较并更新。由于任何实际的子串长度都是一个有限的正值， 因此初始时将其设为无穷大可以确保任何找到的子串长度都会比这个初始值小，从而可以正确地记录下最小长度。 """ res = ChartUtil.make_jieba_word(txt) sorted_data = sorted(res, key=lambda x: x[1], reverse=True) def word_cloud() ->...

### Search before asking - [X] I had searched in the [issues](https://github.com/OpenSPG/KAG/issues?q=is%3Aissue) and found no similar issues. ### Operating system information Linux ### What happened ```python if os.path.exists(input): raise FileNotFoundError(f"File...

使用产品模式，对LLM模型进行配置，一直报连接错误

1

### Search before asking - [x] I had searched in the [issues](https://github.com/OpenSPG/KAG/issues?q=is%3Aissue) and found no similar issues. ### Operating system information Linux ### What happened 我在使用开发者模式是能正常运行的，但是使用产品模式，无法配置大模型参数，配置参数和开发者模式下一致  知识库参数配置点击保存也会出现报错  ###...

How do I use the model checkpoint checkpoint.pt after fine-tuning?

2

After fine-tuning, how should I use the generated model weights checkpoint.pt for inference? Should I directly replace the original model file seamlessM4T_v2_large.pt with checkpoint.pt?