Doubled down on my one-shot finetune Claude experiment with 32 scripts from MrBeast videos. Videos are great because they contain lots of tokens. Also wrote a better prompt this time using XML tags. -I Survived 100 Days On The Moon
-Last To Leave $1,000,000 Mansion Keeps It
CODE
-

Fine-tuning Claude with MrBeast video scripts using XML prompts
By
–
-
New Script Competition Launched on HuggingFace Platform
By
–
A brand new script competition on HuggingFace: https://
huggingface.co/spaces/BVRA/Sn
akeCLEF2024
… -

Box Plot Visualization in Python Using Seaborn Guide
By
–
Box Plot in Python using Seaborn: A Comprehensive Guide: Introduction In data analysis, the ability to visually represent complex datasets is… https://
analyticsvidhya.com/blog/2024/02/b
ox-plot-in-python-using-seaborn/?utm_source=dlvr.it&utm_medium=twitter
… #DataAnalytics #DataScience #DataDriven #Blockchain #BusinessIntelligence #Infrastructure #CIO #BigData -

Llama 7B Training on Single RTX 4090 GPU Memory Efficient
By
–
For the first time, we show that the Llama 7B LLM can be trained on a single consumer-grade GPU (RTX 4090) with only 24GB memory. This represents more than 82.5% reduction in memory for storing optimizer states during training. Training LLMs from scratch currently requires huge
-

Free MLOps Engineering Course: Build Deploy Monitor Models
By
–
The Only Free Course You Need To Become a MLOps Engineer: Unlock the secrets to building, deploying, and monitoring models like a pro. https://
kdnuggets.com/the-only-free-
course-you-need-to-become-a-mlops-engineer?utm_source=dlvr.it&utm_medium=twitter&utm_campaign=the-only-free-course-you-need-to-become-a-mlops-engineer
… -
Vec2text: Inverting Text Embeddings Through Stories
By
–
wrote a little blog post about our vec2text, our method for text embedding inversion! it's like the paper but told as a story: with a lot less jargon, and no math. check it out 🙂
-
VSCode Compatible Platform Launches with Extensions Support
By
–
We're completely VSCode compatible, including your extensions + remote ssh and notebooks
-
MLX Axolotl Google Vertex AI frameworks comparison
By
–
MLX, Axolotl, Google vertex, depends on the cases
-

Silent Bugs in Fine-tuning: Attention to Detail Matters
By
–
Beautiful work / attention to detail trying to get Gemma to finetune correctly. There are so many foot guns here to be super careful with. All of these issues don't throw any errors, they silently make your network worse. A great example of what I wrote about in my "A Recipe for
-
Converting JSONL files to TXT format for upload
By
–
I had them in JSONL, but you can't upload that type of file, so I converted the files to TXT.