-
`pip install stable-baselines3[extra]`
## Repro
```python
from stable_baselines3 import PPO
import torchdynamo
@torchdynamo.optimize("inductor")
def train():
model = PPO("MlpPoli…
-
### 🐛 Describe the bug
Running Torch.compile with Llama7B and FSDP mixed precision, results in assert during first forward pass of training:
(you can repro by going to https://github.com/lessw2020/l…
-
Hello everyone, thank you for the great job!
I am trying to further fine-tune the LLaVA architecture using your implementation with LLaMA 3 Instruct 8B. I can already fine-tune the Vicuna model usi…
-
Can you explain me how to run this code?
-
I am using Ubuntu 22.04 with an AMD RX 5700 graphics card (gfx1010) with the driver being installed with amdgpu-install from the repo.radeon.com repository for version 6.1.3 (amdgpu-install --usecase=…
-
整体报错如下:
\Users\Administrator\miniconda3\envs\python39\lib\site-packages\transformers\models\qwen2\modeling_qwen2.py:580: UserWarning: 1Torch was not compiled with flash attention. (Triggered internal…
kksmi updated
2 weeks ago
-
### 🐛 Describe the bug
When running in torch.compile mode, the following error is encountered:
```
**{'indices': [1, 1, 1, 1], 'input': FakeTensor(..., size=(1, 1))}):
torch.dsplit requires a …
-
(huatuo) root@autodl-container-cec311b53c-c2dea304:~/Huatuo-Llama-Med-Chinese-main# bash ./scripts/finetune.sh
===================================BUG REPORT===================================
Wel…
yihp updated
10 months ago
-
## Bug description
Getting RuntimeError('Event loop is closed') for every 2nd request
## How to reproduce
Prisma client Connect is called once while starting the server as visible below
Th…
-
Hello,
I followed the ReadMe, creating a conda environment, activating it and running the demo with hero_model and vdr dataset according to the section "Setup" and "Running out of the box!".
However…
liu83 updated
1 month ago