-
Error with gemma-7b[-it] but not with gemma-2b[-it]
# Target
- CPU Intel (cuda not used)
- Linux mint 21.2
- Python 3.10.12
# Source code
```python
import jinja2
import torch
from tr…
-
I'm getting some erratic behavior when using `GenerationRequest`.
Some responses are marked as `done` but do not include the data expected in `final_data`.
Here's the output from the call for o…
-
the current project dependencies, `cmake`, `highway`, and `gtest`, are impacting the ease of initial setup. they increase the overhead for new users and contributors. by considering streamlining the p…
-
### Is there an existing issue for the same bug?
- [X] I have checked the troubleshooting document at https://github.com/OpenDevin/OpenDevin/blob/main/docs/guides/Troubleshooting.md
- [X] I have chec…
-
### System Info
```shell
python version : 3.10.12
optimum version : built from github
openvino : 2024.1.0-14548-688c71ce0ed
transformers : 4.38.1
```
### Who can help?
@JingyaHuang @echarlaix
…
-
## 🐛 Bug
Try to run MLC LLM on an iphone, with codeLlama, Got following error:
Check failed: (fload_exec.defined()) is false: TVM runtime cannot find vm_load_executable
It works well for Llama 2.…
-
### System Info
```Shell
accelerate verion: 0.29.1
OS:
python version: 3.10
numpy version: 1.24.4
torch version: 2.1.0
transformer verion: 4.39.3
Accelerate configuration:
- `Accelerate` d…
-
I am fine-tuning `bge-reranker-v2-gemma` with my custom training dataset. I am using 4x NVIDIA A10G with 24GB memory each so it's quite a lot of memory. But, I still get CUDA OOM shortly into the tr…
-
# Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [x] I am running the latest code. Development is very rapid so there are no tagged versions as of…
-
The Google model have 2B model, it seems that we can use less than 4*24GB GPUs to fine-tune with full parameters. Do you plan to support it?