-
When using ORPO to fine-tune mistral-7b-instruct-v0.3-bnb-4bit, after clicking orpo_trainer.train() to start, the following error message appears:
`-------------------------------------------------…
-
Hi, I am getting this issue. I am running it on following system. I followed the instructions given in README.
Windows 11 Home
Intel Core i9
32GB RAM
( I tried with Anaconda and python3.11.9 and…
-
### Astro Info
```block
Astro v5.0.0-beta.5
Node v20.15.0
System Windows (x64)
Package Manager npm
Output st…
-
In Hugging Face "eager" Mistral implementation, a sliding window of size 2048 will mask 2049 tokens. This is also true for flash attention. In the current vLLM implementation a window of 2048 will mas…
caiom updated
3 weeks ago
-
~/MusePose# accelerate launch train_stage_2.py --config configs/train/stage2.yaml
The following values were not passed to `accelerate launch` and had defaults used instead:
`--num_processes`…
-
### Your current environment
The output of `python collect_env.py`
```text
Your output of `python collect_env.py` here
```
### 🐛 Describe the bug
--enable-prefix-caching causing …
-
### 🚀 The feature, motivation and pitch
As we can see, Google Gemini can support up to million tokens and to serve longer context length, we have to do context parallelism, which means, split the i…
-
### Bug description
When launching a game from the steam deck gaming mode, installed using the flatpak version of Lutris 0.5.17, it immediately crashes/fails to launch. Launching the same game from…
Nevon updated
2 months ago
-
Currently the option to create a security group rule only allows RemoteGroupID or RemoteIPPrefix on rule creation, could this be extended to allow the use of remote address groups per the API?
htt…
-
- OS: [LMDE (Linux Mint Debian Version) 6]
- Scrcpy version: 2.6.1
- Installation method: cloning from repo using terminal
- Device model: Tecno LH7n
- Android version: 14
When I tried to …