LLM Farm 4+

Name: LLM Farm
Author: Artem Savkin

Artem Savkin

專為 iPad 設計

- 免費

描述

LLMFarm is an iOS and MacOS app to work with large language models (LLM). It allows you to load different LLMs with certain parameters.

# Features
* Various inferences
* Various sampling methods
* Metal
* Model setting templates
* LoRA adapters support
* LoRA FineTune and Export

# Inferences
* LLaMA
* GPTNeoX
* Replit
* GPT2 + Cerebras
* Starcoder(Santacoder)
* RWKV (20B tokenizer)
* Falcon
* MPT
* Bloom
* StableLM-3b-4e1t
* Qwen

# Multimodal
* LLaVA 1.5 models
* Obsidian
* MobileVLM 1.7B/3B models

Note: For Falcon, Alpaca, GPT4All, Chinese LLaMA / Alpaca and Chinese LLaMA-2 / Alpaca-2, Vigogne (French), Vicuna, Koala, OpenBuddy (Multilingual), Pygmalion/Metharme, WizardLM, Baichuan 1 & 2 + derivations, Aquila 1 & 2, Mistral AI v0.1, Refact, Persimmon 8B, MPT, Bloom select llama inferece in model settings.

Sampling methods
* Temperature (temp, tok-k, top-p)
* Tail Free Sampling (TFS)
* Locally Typical Sampling
* Mirostat
* Greedy
* Grammar (dont work with GGJTv3)

2024年3月25日

版本 1.0.1

If you are getting strange prediction results in version 1.0.1, but everything was fine in version 0.9.0, try disabling the BOS option in the template.

## Changes:
* llama.cpp updated to b2135
* Added support for multimodal models MobileVLM, Yi-VL, LLaVA, Obsidian tested on (mobileVLM 3B)
* Added the ability to download models from the application menu
* Added possibility to specify System Prompt, which will be added to the text of the first message in the session. See (https://github.com/guinmoon/LLMFarm/wiki/FAQ)
* Added ability to clone chat (without message history)
* Added progress indicator for model loading
* Added the ability to hide the keyboard, to do this tap anywhere in the chat window
* Added ability to temporarily disable chat autoscrolling by tapping anywhere in the chat window, autoscrolling will be enabled automatically when sending a new message
* When you clear the message history, the model context is also cleared
* Chats are sorted by last modification date
* Clear chat history button is placed on the toolbox.
* You can now use both {prompt} and {{prompt}} designations in templates
* Templates have been updated
* Fixed disappearing keyboard bug
* Fixed a bug with displaying already deleted chats and models
* Fixed crash on switch model
* Fixed a bug that could cause a crash on startup of feintune
* Fixed some bugs that could cause the application to crash
* Fixed some other bugs
* Some UI improvements