LLMS

–

23 August 2023 16h03

Lit-GPT 🙂 https://
github.com/Lightning-AI/l
it-gpt
…

→ View original post on X — @googleai

TokenSplit Discussion at Interspeech 2023 Google Booth

By

@googleai

–

23 August 2023 16h03

Miss the discussion of TokenSplit on Tuesday? You'll have another chance to hear @ScottTWisdom & @HakanErdoganPhD talk about it today. Just drop by the #Interspeech2023 Google booth at 3:30pm to learn all about it.

Scaling Llama 2 to GPT-3 Size for Performance Comparison

By

–

23 August 2023 15h18

Someone needs to scale up Llama 2 to GPT 3 size. Would be curious how that compares then.

LoRA Services vs Open-Source: Llama 2 Competitive Comparison

By

–

23 August 2023 14h51

Will be interesting how this LoRA-on-demand service will compare to open-source LoRA on prem. Here's a little reminder that open-source Llama 2 compares very favorably to ChatGPT / GPT 3.5

ML Evaluation Metrics and Lit-GPT Evaluation Framework

By

–

23 August 2023 14h10

I have a write-up explaining BLEU, ROUGE, and BERTScore in Chapter 19 of my ML Q and AI book: https://
leanpub.com/machine-learni
ng-q-and-ai/
… Other than that, Lit-GPT has currently the Eleuther AI Evaluation Harness implemented: https://
github.com/Lightning-AI/l
it-gpt/blob/main/tutorials/evaluation.md
…

Supported Models Toggle via Checkpoint Directory Flag

By

–

23 August 2023 14h08

Sure, the same code works for all supported models. You can toggle these via the –checkpoint_dir flag pointing to the directory where you downloaded the model. Here's a list of the currently supported models:

→ View original post on X — @aibreakfast

LLMs run out of text, use AI to generate synthetic training data

By

@aibreakfast

–

23 August 2023 3h01

LLMs are running out of text to train on So they are using the LLMs to create new training text

→ View original post on X — @miketamir

Exécuter Llama 2 sur Mac avec LLM et Homebrew

By

@miketamir

–

23 August 2023 3h01

Run Llama 2 on your own Mac using LLM and Homebrew https://
bit.ly/3KvLpcT #AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @gdb

GPT-3.5 Turbo Fine-tuning Now Live for Early Customers

By

@gdb

–

23 August 2023 0h01

GPT-3.5 Turbo fine-tuning is now live. Early customers have had great results, sometimes reaching GPT-4-level performance or beyond on their specific task. Really excited to see what people will build:

Finetuning Llama 2 7B with Only 13 GB RAM on Single GPU

By

–

22 August 2023 23h54

I forgot to mention the probably most important thing: Finetuning Llama 2 7B this way – only requires 13 GB RAM – and can thus comfortably run on a single GPU