Recording for Saturday's LLM Finetuning event is here! https://
youtu.be/S7o_ITTAh8w Grateful to @langchain @brevdev @replicatehq @anyscalecompute @metaphorsystems @_FireworksAI @phindsearch and everyone who came and hacked! (recording turned out bad unfortunately so unlisted fn)
CODE
-
LLM Finetuning Event Recording Available Now
By
–
-
Clarification on HumanEval benchmark reference
By
–
Ah I can see how that's misleading, I mean HumanEval as in https://
github.com/openai/human-e
val
… -
Essential Data Science Back to School Checklist and Tips
By
–
For all of our #datascience students, here's what you may need for back to school: Common #SQL commands Endless amounts of coffee A passion for storytelling with data What did we miss? Comment below and share
-
Improve Your Data Science Skills with IBM Skillsbuild Courses
By
–
Want to touch up on your data science skills? Check out our learning courses, courtesy of Skillsbuild: https://
ibm.biz/BdMzZN -
RO-ViT: Region-Aware Vision Transformer Pre-Training Method
By
–
Check out RO-ViT, a simple method to pre-train vision transformers in a region-aware manner (using a novel technique called “cropped positional embeddings”) to improve open-vocabulary detection. Learn more and grab the code at https://
goo.gle/3YB7cFC. -
LangSmith Enables App Development Beyond Python and JavaScript
By
–
If you're building apps not in Python/JS, you can still use LangSmith!
-
Code Llama Variants Surpass GPT-4 on HumanEval
By
–
Code Llama was just released 4 days ago. Since then, we already got 1) WizardCoder-34B (
https://
github.com/nlpxucan/Wizar
dLM/tree/main/WizardCoder
…)
2) Phind's finetuned CodeLLama-34B (
https://
phind.com/blog/code-llam
a-beats-gpt4
…) *Both reported to be surpassing GPT-4 on HumanEval. The open source community is amazing! -
Stanford CS224W: Machine Learning with Graphs
By
–
(1) Stanford CS224W: Machine Learning with Graphs – YouTube
https://bit.ly/3wPe1nR #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Improving SQL Question-Answering Systems with LangChain
By
–
We're continuing to do a deep dive on improving question-answering over SQL data Some initial improvements by @fpingham have already made it much more resilient to questions involving text (song titles, artist names, etc) Access it here: https://
sql-langchain.streamlit.app -
Meta Releases Code Llama Foundation Models Family Open Source
By
–
Meta releases the Code Llama foundation models family in open source https://actuia.com/actualite/meta-publie-la-famille-de-modeles-de-fondation-code-llama-en-open-source/
… #AI #artificialintelligence
@Meta