-
I'm running into problems with the relative effect when making the forecast. It always returns much bigger than expected, sometimes goes negative although should be positive. Please find below my code…
-
Hi EconML team, we're getting the below error in our builds:
Wondering if this logic should pass with empty arr in https://github.com/py-why/EconML/blob/479362aceb3205b6515adf5084f59a24ea79785d…
-
### Subject of the issue
_Some_ simple interventional queries can't be resolved due to potentially wrong identification of adjustment-sets.
Interventional query breaks with error message: ValueError…
-
Hi Team,
It is amazing handbook. In the continued pre-training script (`run_cpt.py`), I saw that it is not using "mlm" (Masked Language Model) parameter in the training process. I though that the …
-
https://github.com/RVC-Boss/GPT-SoVITS/blob/4e43f6097fe468cf747237f1088e46b5f4d7724d/GPT_SoVITS/AR/models/t2s_model.py#L123
这个位置diagonal应该=0,需要包括对角线位置,否则这个causal mask就没有包含当前位置,现在的状态应该是预测了未来两步
-
### System Info
Python 3.10.13, CUDA 12.1
GPU = NVIDIA GeForce RTX 2080 Ti. Max memory = 10.747 GB.
torch==2.2.1
torchaudio==2.1.0
torchvision==0.16.0
tokenizers==0.15.2
transformers ==git+ht…
-
使用trl的SFTTrainer + Lora微调,无法保存模型。
训练配置的相关代码如下:
```
deepspeed_config = {
"zero_optimization": {
"stage": 2,
"offload_optimizer": {
"device": "cpu",
…
-
Hello all,
Thanks for your great work here. We are implementing speculative decoding at mistral.rs, and were in the final stages of testing when we discovered some incredibly strange behavior. Spec…
-
Take for example the microservice latency RCA demonstration in the dowhy documentation (https://www.pywhy.org/dowhy/v0.8/example_notebooks/rca_microservice_architecture.html)
It's a fantastic example…
-
I tried to compile `TinyLlama-1.1B-Chat-v1.0` model to vmfb but failed. The parameter data type unmatch in torch.nn.functional.scaled_dot_product_attention(). How can I fix it?
PS. I based on commi…