text-generation-webui-docker VS LLaMA-Adapter

I have been using docker images from here. It can be connected to SillyTavern with API.

Hi guys, I am using Text Gen Webui-docker,I want to load an exl2 model with ExLlamav2_HF. I have tried 34B,13B and 7B,and none of them worked,while I can load it with llama.cpp with .gguf files. Everytime I load the models it gave me sam errors: ``` Traceback (most recent call last):

I'm trying to get the container for text-generation-webui to run, where the setup itself was pretty straight forward.

Here's the dockerized oogabooga link: https://github.com/Atinoda/text-generation-webui-docker

Has anyone gotten Atinoda/text-generation-webui-docker (github.com) working on WSL? I'm having port issues.

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.

Chat65B: https://github.com/ZrrSkywalker/LLaMA-Adapter/tree/main/llama_adapter_v2_chat65b

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.

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

Found relevant code at https://github.com/ZrrSkywalker/LLaMA-Adapter + all code implementations here