brev-cli
EasyLM
| brev-cli | EasyLM | |
|---|---|---|
| 7 | 8 | |
| 198 | 2,253 | |
| 1.5% | - | |
| 7.9 | 5.9 | |
| 4 days ago | about 3 hours ago | |
| Go | Python | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
brev-cli
- Brev: Start fine-tuning and training models in < 10 minutes
- OpenLLaMA: An Open Reproduction of LLaMA
-
Using the cloud or buying a GPU
I don't have a PC right now that will run StableDiffusion. I can build one but I think I'm going to need a pretty powerful GPU which I'm not sure I can afford right now. I started using something called Brev https://brev.dev/ (no, I don't work there just found it searching). It's pretty affordable and super easy to setup.
-
is there a good guide on how to train an ai to simulate your own art work?
I just finished listening to an episode of the Practical AI podcast, where they talked with Nader Khalil from brev.dev. They talked a little bit about setting up dreambooth and training it with ten images in about 4 minutes. I havent tested it, but it is worth a try. Brev.dev is a way to set up virtual machines and developement environments. Would love to heard from people who have used it.
- New AI edits images based on text instructions (instructPix2Pix/imaginAIry)
-
Tensorbook
R.I.P. battery.
Personally I've been using Brev [1] to do my cloud training, you get a cloud GPU instance that you can upgrade/downgrade on the fly, and makes supports VS Code out of the box.
[1] https://brev.dev/
- Brev
EasyLM
- Maxtext: A simple, performant and scalable Jax LLM
- How To Fine-Tune LLaMA, OpenLLaMA, And XGen, With JAX On A GPU Or A TPU
-
Open-sourced LLMs are adept at mimicking ChatGPT’s style but not its factuality. There exists a substantial capabilities gap, which requires better base LM.
Title: The False Promise of Imitating Proprietary LLLs Authors: Arnav Gudibande, Eric Wallace, Charlie Snell, Xinyang Geng, Hao Liu, Pieter Abbeel, Sergey Levine, Dawn Song Word Count: 3400 Average Reading Time: 18-20 minutes Source Code: https://github.com/young-geng/EasyLM Additional Links: https://huggingface.co/young-geng/koala-eval, https://huggingface.co/young-geng/koala
-
Paid dev gig: develop a basic LLM PEFT finetuning utility
Check out easyLM https://github.com/young-geng/EasyLM
-
OpenLLaMA Releases 7B/3B Checkpoints with 700B/600B Tokens
We release the weights in two formats: an EasyLM format to be use with our EasyLM framework, and a PyTorch format to be used with the Hugging Face transformers library.
-
OpenLLaMA: An Open Reproduction of LLaMA
I am quite new to this, I would like to get it running. Would the process roughly be:
1. Get a machine with decent GPU, probably rent cloud GPU.
2. On that machine download the weights/model/vocab files from https://huggingface.co/openlm-research/open_llama_7b_preview...
3. Install Anaconda. Clone https://github.com/young-geng/EasyLM/.
4. Install EasyLM:
conda env create -f scripts/gpu_environment.yml - Koala: A Dialogue Model for Academic Research [Finetuned Llama-13B on a dataset generated by ChatGPT]
What are some alternatives?
sd_dreambooth_extension
mlc-llm - Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
SRNet - A tensorflow reproducing of paper “Editing Text in the wild”
camel - 🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Language Model Society (NeruIPS'2023) https://www.camel-ai.org
open_llama - OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
Open-Llama - The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.
stable-diffusion-webui - Stable Diffusion web UI
RWKV-LM - RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
modal-examples - Examples of programs built using Modal
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.