Back
Yaël 🛸
Load previous page…
#thecompaniesapi watch the data being extracted for our customer ; switch back to phi3 branch again
#thecompaniesapi start a new customer dataset extraction, also tried to run our new LLM on a way smaller GPU with success :)
#thecompaniesapi lunch with @LeCoupa and try new prompt techniques with phi
#thecompaniesapi finalize subpages & sitemap extraction, now our bot can filter out sitemap to only visit pages that contains interesting data for our schema
#thecompaniesapi quantize phi3.5 to 4bit to use it in our inference server; same model size but 128k context length instead of 4k, I can now process huge chunks of texts without relying on batching
#thecompaniesapi continue on phi3; tryin to create the best possible synthesis of a web page at a low cost
#thecompaniesapi continue r&d on phi3, trying idea refinement from structured text content, then pipe to inference flow, unknown territories 🤣
#thecompaniesapi improving results from phi3 is a tedious task, but if it pays off we get rid of a ton of problems
#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
#thecompaniesapi continue phi3 impl now that customer support is clear ; damn that model is fast
#thecompaniesapi cleaning the database ; hotfix for customers
#thecompaniesapi multitasking support & AI stack rewrite; plenty of new things to do and try
#thecompaniesapi continue working on phi3 ; first steps of subdomain support & association ; rewrite most of our AI impl
#thecompaniesapi close some customer support queries
#thecompaniesapi few iterations on our ai flows, trying phi3
#thecompaniesapi deploy new bot ; add per-company sync on robot ; continue tests on phi3
#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
#thecompaniesapi code review & hotfixes deploy on production