Before you even get to multi-GPU training with model parallel frameworks like #Deepspeed, you need to load the pretrained checkpoint into memory. To make matters worse for machines with multiple GPUs, you need to load the checkpoint into host memory once for each GPU in your job!
CODE
-
Agent Retriever Tool Architecture for Decision-Making
By
–
The basic idea: Give an agent a tool that is itself a retriever. The agent can then call this tool and get back a list of documents This allows the agent to decide when it wants to do retrieval – could do it once, twice, or not at all
-
New Memory Type for Agent Tool Invocation Results
By
–
We've also added a new type of memory This type of memory allows for using the results of previous tool invocations in future agent interactions This means if you ask a follow up question, you don't have to do retrieval all over again
-
Conversational Retrieval Agents Replace ConversationalRetrievalChain
By
–
Conversational Retrieval Agents The most popular chain in @langchain is the ConversationalRetrievalChain, which allows you chat with your data Using an agent instead can allow for great flexibility, and its a narrow and well defined enough agent that its fairly reliable
-
Conversational Retrieval Agents: Advanced QA Systems
By
–
I'll dive into details in this thread, but quick links: Blog: https://
blog.langchain.dev/conversational
-retrieval-agents/
… Python Docs: https://
python.langchain.com/docs/use_cases
/question_answering/how_to/conversational_retrieval_agents
… JS Docs: https://
js.langchain.com/docs/use_cases
/question_answering/conversational_retrieval_agents
… -
Bag-of-Words Results for IMDb Movie Review Dataset
By
–
Nice work! I also had the bag-of-words results for the IMDb movie review dataset in my post https://
magazine.sebastianraschka.com/p/large-langua
ge-models-and-nearest
… -
Claude vs Code Interpreter: Early Funding Trends Analysis
By
–
Claude vs Code Interpreter (looking at funded ai companies and who was checking them out on bens bites months before)
-
Auto-generate code to pull API data metrics JSON
By
–
Give API docs
GPT autogenerates code to pull all data/metrics
If additional info required, prompt user (eg: GA API requires project ID, keys)
Formats into JSON and returns -
Building GPT-Based Universal Data Adapter Solutions
By
–
Has anyone built/trying to build a GPT based universal data adapter? Including prompting additional info from the user if need be?