LLM Farm 4+

Artem Savkin

Entwickelt für iPad

    • Gratis

Screenshots

Beschreibung

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)

Neuheiten

Version 1.1.1

Changes:
* llama.cpp updated to b2717
* Phi3, Mamba(CPU only), Gemma, StarCoder2, GritLM, Command-R, MobileVLM_V2, qwen2moe models
* IQ1_S, IQ2_S, IQ2_M, IQ3_S, IQ4_NL, IQ4_XS quntization support
* Performance improvements
* Fixed crash when EOS option is on
* Fixed image orientation
* Added warning about creating a chat without a selected model

Bewertungen und Rezensionen

4,5 von 5
2 Bewertungen

2 Bewertungen

metalhurlant ,

Simple but fast and works

It is not remotely as refined as LM studio (it is pretty barebone) but on an ipad with M1 chip (and if you activate Metal) it runs almost all smaller LLMs fast and reliable. It is not suitable for developing projects in it since you cannot really edit your input history, only delete it, but it is great as an offline mobile environment for short LLM sessions.The quality of output of course depends on the LLMs you install. I recommend smaller LLMs since the ipads capacities, though astonishing, are limited.
The best thing is you can make it run almost all smaller LLMs LM studio can run and download.
Thank you for publishing this.

App-Datenschutz

Der Entwickler, Artem Savkin, hat darauf hingewiesen, dass die Datenschutzrichtlinien der App den unten stehenden Umgang mit Daten einschließen können. Weitere Informationen findest du in den Datenschutzrichtlinien des Entwicklers.

Keine Daten erfasst

Der Entwickler erfasst keine Daten von dieser App.

Die Datenschutzpraktiken können zum Beispiel je nach den von dir verwendeten Funktionen oder deinem Alter variieren. Weitere Infos

Das gefällt dir vielleicht auch

Enchanted LLM
Entwickler-Tools
ChatOnMac.com — AI Chat Bots
Entwickler-Tools
AWS IoT Sensors
Entwickler-Tools
Server: Host Files Locally
Entwickler-Tools
Jellycuts
Entwickler-Tools
NanoBeacon BLE Scanner
Entwickler-Tools