Huge! Technology should be accessible to everyone, and not gated by a select few. Thank you @ylecun
, @Ahmad_Al_Dahle
, @rsumbaly
, @Meta for making this possible for all!
@jiquanngiam
-
Meta Makes AI Technology Accessible to Everyone
By
–
-
Fine-tuning Llama-3.1-8B with High-Quality Reasoning Datasets
By
–
What I'm excited about: Use Llama-3.1-405B to generate a high quality reasoning dataset, then fine-tune Llama-3.1-8B models.
— Jiquan Ngiam (@JiquanNgiam) 23 juillet 2024
Imagine having 4o-mini performance models, but open sourced, and tuned for your use cases. pic.twitter.com/mf9tMZ8vWMWhat I'm excited about: Use Llama-3.1-405B to generate a high quality reasoning dataset, then fine-tune Llama-3.1-8B models. Imagine having 4o-mini performance models, but open sourced, and tuned for your use cases.
-
Democratizing Software Engineering Power for All Knowledge Workers
By
–
Love it. Enabling all knowledge workers to be able to fully use computing power. Giving the powers of software engineering to non-engineers. This resounds a lot with what we're building @Lutra_AI
-
Large Models Training Smaller Models: Data Generation Strategy
By
–
I think it only works when you have a larger model produce data for a smaller one. Otherwise the large model -> same large model, without any other external signals, will likely just learn something very similar
-
Llama-3.1-405B for Training Dataset Generation
By
–
Who's going to use Llama-3.1-405B to generate the best training dataset for small models?
-
Open Source to Dominate: Smaller Models Over Large Language Models
By
–
This also means that Open Source is going to dominate in the future – training and serving smaller models is more accessible to many. The large models are going to useful for generating and filtering data, while the smaller models (e.g., 4o-mini) are the ones we want deployed.
-
Small Models Large Context Windows: The Winning LLM Formula
By
–
The winning formula for LLMs is going to be (a) small model, (b) large context window, (c) strong reasoning ability. The quality cost trade off makes this clear: https://
x.com/swyx/status/18
15037679014388172
… Large context window will enable a lot of applications (prompt instructions, RAG) as long -
Latest AI Model Achieves 16K Output Tokens Per Request
By
–
and… 16K output tokens per request! much under- rated feature of the latest model.
-
Scaling Engineering Teams: Why More Bodies Don’t Mean Faster Code
By
–
maybe more relatable…. 1 engineer can make a simple code change in 10mins, but 10 engineers cannot change the same part of the code in 1 min. 1 engineer can change a light bulb in 10 mins, but 10 engineers cannot change the same light bulb in 1 min.
-
Anthropic Advances Larger Output Token Capacity for Data Processing
By
–
Finally! We need models with much larger output tokens and excited to see @AnthropicAI make progress here! There's a ton of data processing tasks (e.g., extractions of big lists) that benefit from this and we're excited to try it out.