LLaMA-Adapter
open_llama
LLaMA-Adapter | open_llama | |
---|---|---|
16 | 52 | |
4,021 | 7,211 | |
- | 0.9% | |
9.4 | 5.3 | |
11 months ago | 10 months ago | |
Python | ||
GNU General Public License v3.0 only | 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.
LLaMA-Adapter
- Are you selfhosting a ChatGPT alternative?
-
Best general purpose model for commercial license?
Either LLaMA with Alpaca LoRA 65B, or LLaMA-Adapter-V2-65B chat demo. I haven't seen any tests of the 65B LLaMA-Adapter-V2, but they claim it's as good as ChatGPT when compared using GPT-4.
-
LLaMA-Adapter V2: fine-tuned LLaMA 65B for visual instruction, and LLaMA Chat65B trained with ShareGPT data for chatting. Chat65B model has been released.
Chat65B: https://github.com/ZrrSkywalker/LLaMA-Adapter/tree/main/llama_adapter_v2_chat65b
-
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
How to efficiently transform large language models (LLMs) into instruction followers is recently a popular research direction, while training LLM for multi-modal reasoning remains less explored. Although the recent LLaMA-Adapter demonstrates the potential to handle visual inputs with LLMs, it still cannot generalize well to open-ended visual instructions and lags behind GPT-4. In this paper, we present LLaMA-Adapter V2, a parameter-efficient visual instruction model. Specifically, we first augment LLaMA-Adapter by unlocking more learnable parameters (e.g., norm, bias and scale), which distribute the instruction-following ability across the entire LLaMA model besides adapters. Secondly, we propose an early fusion strategy to feed visual tokens only into the early LLM layers, contributing to better visual knowledge incorporation. Thirdly, a joint training paradigm of image-text pairs and instruction-following data is introduced by optimizing disjoint groups of learnable parameters. This strategy effectively alleviates the interference between the two tasks of image-text alignment and instruction following and achieves strong multi-modal reasoning with only a small-scale image-text and instruction dataset. During inference, we incorporate additional expert models (e.g. captioning/OCR systems) into LLaMA-Adapter to further enhance its image understanding capability without incurring training costs. Compared to the original LLaMA-Adapter, our LLaMA-Adapter V2 can perform open-ended multi-modal instructions by merely introducing 14M parameters over LLaMA. The newly designed framework also exhibits stronger language-only instruction-following capabilities and even excels in chat interactions. Our code and models are available at https://github.com/ZrrSkywalker/LLaMA-Adapter.
- Surpasses ChatGPT on Some Tasks
- [News] This language model surpasses ChatGPT on some prompts
-
Meet LLaMA-Adapter: A Lightweight Adaption Method For Fine-Tuning Instruction-Following LLaMA Models Using 52K Data Provided By Stanford Alpaca
Quick Read: https://www.marktechpost.com/2023/03/31/meet-llama-adapter-a-lightweight-adaption-method-for-fine-tuning-instruction-following-llama-models-using-52k-data-provided-by-stanford-alpaca/ Paper: https://arxiv.org/pdf/2303.16199.pdf Github: https://github.com/ZrrSkywalker/LLaMA-Adapter
- LLaMA-Adapter: Efficient Fine-Tuning of LLaMA
-
[R] LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Found relevant code at https://github.com/ZrrSkywalker/LLaMA-Adapter + all code implementations here
- You can now fine-tune LLaMA to follow instructions within ONE hour
open_llama
-
How Open is Generative AI? Part 2
The RedPajama dataset was adapted by the OpenLLaMA project at UC Berkeley, creating an open-source LLaMA equivalent without Metaβs restrictions. The model's later version also included data from Falcon and StarCoder. This highlights the importance of open-source models and datasets, enabling free repurposing and innovation.
-
GPT-4 API general availability
OpenLLaMA is though. https://github.com/openlm-research/open_llama
All of these are surmountable problems.
We can beat OpenAI.
We can drain their moat.
-
Recommend me a computer for local a.i for 500 $
#1: π Open-source Reproduction of Meta AIβs LLaMA OpenLLaMA-13B released. (trained for 1T tokens) | 0 comments #2: π #1 on HuggingFace.co's Leaderboard Model Falcon 40B is now Free (Apache 2.0 License) | 0 comments #3: π Have you seen this repo? "running LLMs on consumer-grade hardware. compatible models: llama.cpp, alpaca.cpp, gpt4all.cpp, rwkv.cpp, whisper.cpp, vicuna, koala, gpt4all-j, cerebras and many others!" | 0 comments
-
Who is openllama from?
Trained OpenLLaMA models are from the OpenLM Research team in collaboration with Stability AI: https://github.com/openlm-research/open_llama
-
Personal GPT: A tiny AI Chatbot that runs fully offline on your iPhone
I can't use Llama or any model from the Llama family, due to license restrictions. Although now there's also the OpenLlama family of models, which have the same architecture but were trained on an open dataset (RedPajama, the same dataset the base model in my app was trained on). I'd love to pursue the direction of extended context lengths for on-device LLMs. Likely in a month or so, when I've implemented all the product feature that I currently have on my backlog.
-
XGen-7B, a new 7B foundational model trained on up to 8K length for 1.5T tokens
https://github.com/openlm-research/open_llama#update-0615202...).
XGen-7B is probably the superior 7B model, it's trained on more tokens and a longer default sequence length (although both presumably can adopt SuperHOT (Position Interpolation) to extend context), but larger models still probably perform better on an absolute basis.
-
MosaicML Agrees to Join Databricks to Power Generative AI for All
Compare it to openllama. It github doesn't have a single script on how to do anything.
-
Databricks Strikes $1.3B Deal for Generative AI Startup MosaicML
OpenLLaMA models up to 13B parameters have now been trained on 1T tokens:
https://github.com/openlm-research/open_llama
-
Containerized AI before Apocalypse π³π€
The deployed LLM binary, orca mini, has 3 billion parameters. Orca mini is based on the OpenLLaMA project.
-
AI β weekly megathread!
OpenLM Research released its 1T token version of OpenLLaMA 13B - the permissively licensed open source reproduction of Meta AI's LLaMA large language model. [Details].
What are some alternatives?
LoRA - Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
gpt4all - gpt4all: run open-source LLMs anywhere
llama.cpp - LLM inference in C/C++
bench-warmers - DigThatData's Public Brainstorming space
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.
chatgpt-telegram-bot - π€ A Telegram bot that integrates with OpenAI's official ChatGPT APIs to provide answers, written in Python
text-generation-webui-docker - Docker variants of oobabooga's text-generation-webui, including pre-built images.
gorilla - Gorilla: An API store for LLMs
ggml - Tensor library for machine learning
gpt-json - Structured and typehinted GPT responses in Python