h/t to @PiotrCzapla for noticing I had a bug that meant there's no batchnorm in those models! After fixing, my new best results: Epochs / c
5 / 93.0
20 / 94.5
50 / 94.9
CODE
-
Bug Fix Improves Model Accuracy to 94.9 Percent
By
–
-
Post-Copilot Directions from Anshul and Codeium Team
By
–
see also the proposed post-Copilot directions from @_anshulr and the @codeiumdev team on last week's post
-
Embeddings as Versioned Documentation for Machine-Readable Code
By
–
my take: Docs for humans, Embeddings for machines Write samples -> get embeddings -> ship with each API/SDK version composable give users 99% accurate codegen can't version foundation models, but can version embeddings If you liked @types
, you'll *LOVE* @embeddings! -
Beyond Copilot: The Next Evolution in AI Developer Experience
By
–
The Big Question in AI-driven developer experience: What's after Copilot? Everyone is convinced this is "just" the beginning but can't articulate what the next killer form factor will be. Increasingly convinced next step change won't be from optimal stuffing context windows
-
Customizable AI Response Prefix in Conversational Memory
By
–
More customizability for conversational memory A small change, but allows for specification of the prefix to use for for the AI response Was previously hardcoded to "AI", but can now be set to whatever Idea came from the discord! https://
langchain.readthedocs.io/en/latest/exam
ples/memory/conversational_customization.html
… -
LangChain Improves Memory Documentation Organization
By
–
Improved memory docs In order to keep up with all these changes to memory, we also revamped the memory docs slightly to be more organized https://
langchain.readthedocs.io/en/latest/exam
ples/memory.html
… As always, let us know if you have feedback! -
New Memory Type Combining Summary and Context Window
By
–
New memory type Previously, we had one memory type that created a summary, another that kept a window of recent lines of conversation. jaloo555 added a new type of memory which does both! It decides the window based on token length. https://langchain.readthedocs.io/en/latest/examples/memory/conversational_memory.html#ConversationSummaryBufferMemory
-
Weaviate Vectorstore: New add_texts Method Implementation
By
–
add_texts for @weaviate_io The @weaviate_io vectorstore implementation was previously missing an `add_texts` method @CShorten30 added one! This allows you to easily insert embeddings (eg, of examples for the example selector)
-
Map-Reduce and Refine Chains Now Return Intermediate Steps
By
–
Return intermediate steps for map-reduce & refine chains @johnjnay had the great idea to allow for returning of intermediate steps of these chains to the user This makes it easy to inspect things like Q&A over each document, before combining https://
langchain.readthedocs.io/en/latest/exam
ples/data_augmented_generation/question_answering.html#The-map_reduce-Chain
… -
Mixed Precision Training: Complexity Beyond High Level Concepts
By
–
the high level picture is easy enough but keeping track of the mixed precision around the whole network, the dynamical behavior of the values and ranges, the support for them and their conversions across all the various kernels and library versions everywhere, is the nightmare