Back
Similar todos
#thecompaniesapi tests are over; phi3 is what we need; dropping lots of python code in favor of a single inference process to govern them all
See similar todos
#thecompaniesapi start working on fine tuning as phi3 cannot stop hallucinating even though its a lot faster, heard it would possibly change everything for our usecase so its worth trying
See similar todos

No replies yet

#thecompaniesapi continue r&d on phi3, trying idea refinement from structured text content, then pipe to inference flow, unknown territories 🤣
See similar todos

No replies yet

#thecompaniesapi few iterations on our ai flows, trying phi3
See similar todos

No replies yet

#thecompaniesapi run my phi3-128k flow using llama3.1 and the results are mind blowing, it's insane how good llama is at conserving context and original purpose even when supplied with thousands of tokens; also shipped multiple hotfixes in robot UI; about to merge a month of work and then hop on fine tuning
See similar todos

No replies yet

cache recs for longer to save on model inference costs #pango
See similar todos

No replies yet

#thecompaniesapi continue working on phi3 ; first steps of subdomain support & association ; rewrite most of our AI impl
See similar todos

No replies yet

#thecompaniesapi watch the data being extracted for our customer ; switch back to phi3 branch again
See similar todos

No replies yet

play with different inference settings to make deployment more efficient #ai
See similar todos

No replies yet

#thecompaniesapi port back my ai wrapper improvements on our existing llama stack and prepare fine tuning for phi3
See similar todos

No replies yet

#thecompaniesapi port back my ai wrapper improvements on our existing llama stack and prepare fine tuning for phi3
See similar todos

No replies yet

#thecompaniesapi continue on phi3; hell of a refactor
See similar todos

No replies yet

#thecompaniesapi improving results from phi3 is a tedious task, but if it pays off we get rid of a ton of problems
See similar todos

No replies yet

#thecompaniesapi continue work on phi, lots of iterations, kinda exhausted lately
See similar todos

No replies yet

deploy new #photoai multi depth model with more samplers and textual inversions
See similar todos

No replies yet

export ~5000 crisp conversations and topic model #mused
See similar todos

No replies yet

Create DB dataframes for faster inference
See similar todos

No replies yet

Learned how quantization works! #llms
See similar todos

No replies yet

#thecompaniesapi working on llama3.1 with large context window, trying to improve some parts of our AI flow before merging it; now properly respects industries & naics constraints for current sample
See similar todos

No replies yet

#thecompaniesapi maintenance on the bot ; send back test csv to a big ai company that want to use our api ; start migration to phi3 for ou AI stack
See similar todos

No replies yet