LLM Farm 4+
Run LLM
Artem Savkin
Designed for iPad
-
- Free
Screenshots
Description
Load and test large language models with different parameters locally on your device. Now with support for multimodal models.
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)
What’s New
Version 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
App Privacy
The developer, Artem Savkin, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy.
Data Not Collected
The developer does not collect any data from this app.
Privacy practices may vary based on, for example, the features you use or your age. Learn More
Information
- Provider
- Artem Savkin
- Size
- 16.8 MB
- Category
- Developer Tools
- Compatibility
-
- iPhone
- Requires iOS 16.0 or later.
- iPad
- Requires iPadOS 16.0 or later.
- Mac
- Requires macOS 13.0 or later and a Mac with Apple M1 chip or later.
- Apple Vision
- Requires visionOS 1.0 or later.
- Languages
-
English
- Age Rating
- 4+
- Copyright
- © Artem Savkin
- Price
- Free