Jim Zieleman

icon indicating a website link http://www.zieleman.dev/ icon indicating an email [email protected]

icon location Virginia icon location I am an applied data scientist and full stack developer. I have experience in NLP, CV, and finance. http://www.zieleman.dev/ https://medium.com/@zieleman

Results 17 comments of Jim Zieleman

v2 revised

Okay made the changes and fixed the readme also. I think this is getting close to good to go for the basis of localgptV2

Handling ingestion file types

Wow yeah this is awesome. I think this is all really darn good! Since ingest is also separate from the localgpt class most of these changes wont be too big...

Handling ingestion file types

I agree that we go with the route @teleprint-me has designed.

very slow GPU compared with CPU

if you use the nvidia-smi command, what is your vram usage?

Suggestion to improve or fine tune the model with custom documents

You can try upgrading to a better sentence transformer. Increase chunksize for documents and also increase number of source documents to recall.

multi-user or async prompt requests crashes the app

You will need to create a queue in the api. To manage incoming requests. So u need to wait for a request to complete then serve the next request. If...

sync command --stat does not report correct rm command quantity

Is there a way to do s3 to s3 sync?