maolong Li

Error as follows: ``` Traceback (most recent call last): File "train.py", line 59, in model.fit(x_train, y_train, x_valid, y_valid, epochs=30, batch_size=32, callbacks=callbacks) File "/home/mlli6/venv/lib/python3.6/site-packages/anago/wrapper.py", line 87, in fit shuffle=shuffle) File "/home/mlli6/venv/lib/python3.6/site-packages/anago/trainer.py",...

can't not run with python3

7

Environment : python3.6, Centos 7. code in `lib/gcforest/layers/fg_pool_layer.py`: ``` class FGPoolLayer(BaseLayer): def __init__(self, layer_config, data_cache): """ Pooling Layer (MaxPooling, AveragePooling) """ super(FGPoolLayer, self).__init__(layer_config, data_cache) self.win_x = self.get_value("win_x", None, int, required=True)...

I want to use async create of openai. But the default mode can only use sync get response. When an use summarize mode in ListIndex, it raise an error: ```...

Although the code is not released, I tested it on Tongyi APP, prettty good!

7

在通义APP上试了（男生，女生和小孩），不得不说，效果还是很惊艳的，可以早日开放API使用。 虽然在github上占坑，虚空开源做法有点离谱，但是效果确实可以，希望以后不要搞这种幺蛾子了。 如果不打算开源，只搞个github.io项目主页就好，不然真的败好感。 --------------- I tested it on the Tongyi app (with settings for male, female, and child), and I must say, the results are quite impressive. It would be...

The speed is slower than fast-whisper, is something wrong in my config?

2

The model is used is `Belle-2/Belle-whisper-large-v3-zh` which is a finetuned model of `openai/whisper-large-v3`. Both `whisper-v3` but with different weigths. When i use **fast-whisper(fp16, bs=1)** to transcribe a audio with **220.46s**,...

[Docs] Compared with vllm, lmdeploy has less throughput. Is there any config wrong?

7

### 📚 The doc issue Both of the prompt is: >Here is a conversation(date:2024-04-13) where the assistant reminds the user as their product is about to expire: ''' assistant: 哎，你好，请问你是张三吗？...

awesome! Will integrate into the Fooocus?

3

Will this integrate into the image2image in Fooocus?

This test shows the exl2 quant is the best:`https://huggingface.co/blog/wolfram/llm-comparison-test-llama-3` Will you to test it?