LLMS - AI Dynamics

OpenAI Releases GPT-4 Updates with Function Calling and Cost Reductions

By

–

13 June 2023 20h22

OpenAI GPT-4 and gpt-3.5-turbo updates – new function calling capability in the Chat Completions API
– updated and more steerable versions of gpt-4 and gpt-3.5-turbo
– new 16k context version of gpt-3.5-turbo (vs the standard 4k version)
– 75% cost reduction on sota embeddings

→ View original post on X — @_akhaliq

13 June 2023

OpenAI Functions Release: LangChain Support for Chat Models

By

@hwchase17

–

13 June 2023 20h10

Emergency OpenAI Functions Release `pip install langchain==0.0.199` Support for functions in chat model wrapper Convert @langchain tools to functions Docs: https://
github.com/hwchase17/lang
chain/blob/master/docs/modules/agents/tools/tools_as_openai_functions.ipynb
… Next up… I think its time for a new type of agent

→ View original post on X — @hwchase17

13 June 2023

OpenAI Releases Tool Use for GPT-4 API

By

@danshipper

–

13 June 2023 19h24

Wow! @OpenAI released tool use as part of the new GPT-4 API. This unblocks a huge barrier to building effective agents https://
openai.com/blog/function-
calling-and-other-api-updates
…

→ View original post on X — @danshipper

13 June 2023

GPT-4 and GPT-3.5 Turbo API gain custom function calling

By

@openai

–

13 June 2023 19h16

GPT-4 and GPT-3.5 Turbo models in the API now support calling your custom functions, allowing the model to use tools you design for it. Also — reduced pricing & new model versions (including 16k context for 3.5 Turbo):

→ View original post on X — @openai

13 June 2023

OpenAI Releases Function Calling and Extended Context for GPT-3.5-turbo

By

@sama

–

13 June 2023 19h09

lots of good updates including function calling and 16k context 3.5-turbo:

→ View original post on X — @sama

13 June 2023

FastChat-T5 Encoder-Decoder Model Performs Well on Chatbot Arena

By

@yitayml

–

13 June 2023 17h55

Yeah but fastchat-t5 ranking decently for it's size on chatbot arena is a pretty good evidence of encoder decoder models being able to actually chat well.

→ View original post on X — @yitayml

13 June 2023

LLaMA-Adapter and LoRA: Multimodal Input Advantages

By

@rasbt

–

13 June 2023 17h48

Good question. I'd say LLaMA-Adapter and LoRA are both good methods. The advantage of LLaMA-Adapter though is that you can also embed multimodal inputs (images and others)

→ View original post on X — @rasbt

13 June 2023

List of Open Language Models for Commercial Use

By

@miketamir

–

13 June 2023 17h37

GitHub – eugeneyan/open-llms: A list of open LLMs available for commercial use. https://bit.ly/3MG7VRA #AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @miketamir

13 June 2023

LoRA Implementation Added to Lit-Parrot Project

By

@rasbt

–

13 June 2023 17h16

Just added LoRA the other day (PR still in progress: https://
github.com/Lightning-AI/l
it-parrot/pull/128#pullrequestreview-1477273133
…) and will do some comparisons soon!

→ View original post on X — @rasbt

13 June 2023