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
…
LLMS
-
LoRA Quantization and Evaluation Scripts for Llama-2 Models
By
–
-
Language-to-Reward System Enables Natural Language Robot Control
By
–
Introducing a new language-to-reward system for interfacing LLMs with robots using reward functions. Learn how the system’s predictive control tool enables users to teach robots novel actions using natural language inputs → https://t.co/cLPgwuvvon pic.twitter.com/fxkIKv8bgR
— Google AI (@GoogleAI) 22 août 2023Introducing a new language-to-reward system for interfacing LLMs with robots using reward functions. Learn how the system’s predictive control tool enables users to teach robots novel actions using natural language inputs → https://
goo.gle/44kjHXx -
Ludwig AI 0.8: Open-source LLM framework with fine-tuning
By
–
ICYMI: Last week we released @ludwig_ai 0.8—the first open-source, low-code framework optimized for efficiently building #custom #LLMs with your private data. Check out the webinar replay to see it in action including #finetuning: https://
pbase.ai/45jS7L8 -
Specialists vs Generalists: When Task-Specific Models Outperform GPT
By
–
There are instances where “doing well on one specific task” is better than being “a generalist”. GPT-3.5 and GPT-4 are generalists. They perform reasonably well on many language tasks without having to adapt them to any of those tasks, but their performances are limited in
-
OpenAI Launches GPT-3.5 Turbo Fine-tuning Capabilities
By
–
We've just launched fine-tuning for GPT-3.5 Turbo! Fine-tuning lets you train the model on your company's data and run it at scale. Early tests have shown that fine-tuned GPT-3.5 Turbo can match or exceed GPT-4 on narrow tasks: https://
openai.com/blog/gpt-3-5-t
urbo-fine-tuning-and-api-updates
… -
QLoRA Single-GPU Limitations and Multi-GPU Future Plans
By
–
QLoRA right now it's single-GPU. I left multi-GPU support as a future todo since I am currently mostly focused on the NeurIPS LLM challenge. But it might well be working with multi-GPU settings already; it's just that I haven't tested. Could be that it requires switching from
-
Meta’s SeamlessM4T Models Now Available on Hugging Face
By
–
The new SeamlessM4T models from @MetaAI are now available on Hugging Face! https://
huggingface.co/models?search=
facebook/seamless-m4t
… -
LLMs Environmental and Educational Harms Demand Immediate Action
By
–
AI community I’ve been a part for ten years! Who needs “sentient” AI when LLMs use SO MUCH water now & harm students bc people think they’re cheating & steal IP? Who needs long term “potential harms?” The REAL harms are HERE NOW. Ban LLMs until they don’t harm people & planet.
-
QLoRA Support Added to Lit-GPT for All LLM Models
By
–
Just added QLoRA support for all LLMs in Lit-GPT: Llama 2, Falcon, Pythia, StableLM, and all others! You can use it via `python finetune/lora.py –quantize "bnb.nf4"` to save significant GPU memory. I've ran a few more benchmarks on the Gh PR here: https://
github.com/Lightning-AI/l
it-gpt/pull/275
… -
LLMs water consumption hidden environmental cost of AI
By
–
The soundtrack of climate change is definitively weed whacked and lawn mowers. If anyone ever invented tools that more provide a sense of being able to control and manipulate nature, let me know. Oh, right – LLMs and their water use. But they’re silent and hidden.