-
### Model Series
Qwen2.5
### What are the models used?
Qwen2.5-7b-base
### What is the scenario where the problem happened?
sft with huggingface trainer
### Is this a known issue?
…
hxs91 updated
2 weeks ago
-
### Your current environment
vllm==0.6.1
### How would you like to use vllm
Steps to reproduce
This happens to Qwen2.5-32B-Instruct-AWQ
The problem can be reproduced with the following steps:
…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Problem description
When attempting to attach a sketch or a datum plane to a face and then align them to the m…
-
### Your current environment
Below is my current Docker Compose configuration:
```yaml
services:
vllm:
image: vllm/vllm-openai:v0.6.4
deploy:
resources:
reservation…
-
### Search before asking
- [X] I have searched the HUB [issues](https://github.com/ultralytics/hub/issues) and [discussions](https://github.com/ultralytics/hub/discussions) and found no similar quest…
-
### Motivation.
take a look at the current llama forward computation logic:
```python
class LlamaMLP(nn.Module):
def forward(self, x):
gate_up, _ = self.gate_up_proj(x)
x…
-
### Your current environment
The output of `python collect_env.py`
N/A; happened to multiple users.
### Model Input Dumps
_No response_
### 🐛 Describe the bug
We have been receiving re…
-
### 🚀 The feature, motivation and pitch
I'm encountering an issue with the `weights_only=True` parameter in `torch.load`, where I need to load custom model classes while ensuring repeatable results a…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
### Your current environment
### Environment Details
Running in a Kubernetes environment with Habana Gaudi2 accelerators:
- **Hardware**: Habana Gaudi2 accelerators
- **Deployment**: Kubernetes …