OPEN SOURCE

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 — @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 — @mjasay

Open Sourcing Prompts: The New Code Sharing Model

By

@mjasay

–

23 August 2023 0h52

The idea of open sourcing prompts keeps coming up. @monkchips first clued me into the idea using Midjourney: you see and learn from others' prompts. If prompt engineering is a new way to code (as @mikeloukides has noted), then "open sourcing" prompts makes sense

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

22 August 2023

LoRA Quantization and Evaluation Scripts for Llama-2 Models

By

–

22 August 2023 23h32

Qualitatively, you can use python generate/lora.py –lora_path '… .pth' –quantize "bnb.nf4" –precision "bf16-true" –checkpoint_dir "…/Llama-2-7b-hf" Quantitatively, you can use the python eval/eval_harness scripts: https://
github.com/Lightning-AI/l
it-gpt/tree/main/eval
…