Seungju
Hello, I'm wondering how the log-mel spctrograms are normalized to have zero mean value. The paper mentioned about it, and the masking value is 0 because they have zero mean....
Hello, thanks for your nice implementation of mel-gan. I guess mel-gan can be used as the universal vocoder, and I thought there were a mention about multi-speaker training scheme in...
Hello, I saw that you used `pad`, `audio_slice_frames`, `sample_frames` but I can't understand the usage of those params. Can you explain the meanings of them? Also, `WaveRNN` model was using...
Tested with own fine-tuned 7B alpaca model ``` python inference.py \ --model_name_or_path {model_path} ``` ``` Instruction: Tell me about alpacas. | 2499 | Al | -15.960 | 0.00% | 29886...
Current flash_attn only allows some GPUs (e.g. A100) to use it (https://github.com/haotian-liu/LLaVA/issues/153), and using torch 2.0 implemented flash attention allows other GPUs like A6000.
https://github.com/allenai/OLMo/issues/460, tested with a simple snippet as below: ``` import transformers, torch model = transformers.AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B-Instruct", use_flash_attention_2="flash_attention_2", trust_remote_code=True).cuda() tokenizer = transformers.AutoTokenizer.from_pretrained("allenai/OLMo-7B-Instruct", trust_remote_code=True) print(tokenizer.decode(model.generate(torch.tensor(tokenizer.encode("Hello World! My name is")).unsqueeze(0).cuda())[0])) # Hello World! My...