Yeah. But unless you want to have a generalist model for all languages, is it really that useful to have a MoE approach compared to say the CodeLlama-34B-Python version? I mean eventually things might move to MoE but maybe it’s not that big of a deal atm.
LLMS
-
Current LLM Hallucination Benchmarks: Evaluating Factual Accuracy
By
–
What interesting benchmarks on LLM hallucinations exist currently?
-
Team Pushing Hard on Model Improvements Concrete Examples
By
–
Send any concrete examples you have, the team is pushing very hard on model
Improvements. -
205+ Must-Try ChatGPT Prompts for 2023
By
–
205+ ChatGPT Must-Try ChatGPT prompts https://
godofprompt.ai/blog/205-chatg
pt-prompts-you-cant-live-without-in-2023
… #prompts #chatgptprompt #promptforbusiness #promptchallenge -
Current State of Generative Design in Drug Discovery
By
–
Where is generative design in drug discovery today? https://
bit.ly/3OMRrbq #AI #MachineLearning #DeepLearning #LLMs #DataScience -
LangChain Batch Interface Concurrency Optimization Guide
By
–
you can use the `.batch` interface (see here: https://
python.langchain.com/docs/guides/ex
pression_language/interface#batch
…) and set `max_concurrency` to determine the max concurrency (see example of that here: https://
python.langchain.com/docs/modules/d
ata_connection/retrievers/multi_vector#summary
…) -
LangChain Twitter Fine-tuning Example Repository
By
–
example of that here: https://
github.com/langchain-ai/t
witter-finetune
… -
Karpathy’s GPT State of the Art Talk Remains Insightful
By
–
This talk, "The state of GPT" by Karpathy, I have watched it multiple times and always surprised of how it still feels new. The talk covers the training paradigms of GPT assistant models, common prompting techniques, retrieval-augmented LLMs, …, and practical recommendation
-
GPU constraints influence research direction choices
By
–
One might argue that with more GPUs, they would have worked on BLOOM 2 instead of QLoRA etc.
-
Gmail ChatLoader Integration for Email Model Finetuning
By
–
Over the weekend, I added a GMail ChatLoader integration to @langchain
, to help anyone to finetune models on their emails I evaluated it the old fashioned way – the eyeball test Here's how it did responding to various types of inquiries (VC, customer, integration, @swyx
)