Chansung Park
Chansung Park
when I set pad token 0 and padding=True, the generated text for the padded prompt shows always
not sure when I am going to shutdown, but I will leave this for few hours at least (running on RTX5000). maybe I will put things up in GKE later...
7B demo link: https://notebooksd.jarvislabs.ai/tz0hyvPyQMO0qXbeTpLYv2Wu5-j9AfFm_dM9sQN5fqFGI0lT90sAIHgT-Gi0jLcX/
I have put the links of both one in this repository : https://github.com/deep-diver/Alpaca-LoRA-Serve I used A100 40GB to train both one. I didnt' change the script provided in this repository,...
I hope you guys find it useful. Here is the repo : https://github.com/deep-diver/Alpaca-LoRA-Serve and I am currently running 30B version on my VM. Try it while it is live. Share...
I have shared the one at #87 , and it it still running. Today, I want to share a little modified version of it running on a separate A6000 instance....
for those of you know the project `Alpaca-LoRA-Serve`, I have updated the project to include other models besides `Alpaca-LoRA`. The screenshot shows a GUI menu that you can choose a...
There is a model called SOLAR. This model follows the same architecture as LLaMA2, but it has more layers which make it outstanding performer better than Mistral and even Mixtral...
### Describe the bug when events are chained, and there is an event with JavaScript handler in between, the chain of events can not be canceled. I verified this issue...
This is a custom TFX component project idea. hope to get some feedbacks from (@rcrowe-google , @hanneshapke , @sayakpaul , @casassg) Temporary Name of the component: LLMEvaluator Behaviour : LLMEvaluator...