LLM Farm 4+
Run LLM
Artem Savkin
Designed for iPad
-
- Free
Screenshots
Description
Now with markdown support.
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
* Gemma
* Phi
* Mamba
* Others
# 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 1.3.0
Changes:
* LLaMA.cpp updated to b3190
* Added support for DeepseekV2, GPTNeoX (Pythia and others)
* Added support for Markdown formatting
* Added support for using history in Shortcuts
* Added Flash Attention support
* Added NPredict option
* Save/Load context state. Now it is possible to continue the dialog with the model even after the program is reopened.
* Chat settings such as sampling are now applied without reloading the chat.
* Skip tokens option. Allows you to specify tokens that will not be displayed in the results. May be useful for phi3 and qwen.
* Metal and CPU inference improvements
* Sampling and eval improvements
* Some fixes for phi-3 and MiniCPM
* Fixed some errors
* Added Qwen template
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 has not identified itself as a trader for this app. If you are a consumer in the European Economic Area, consumer rights do not apply to agreements between you and the provider.
- Size
- 19.9 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