
LLM Farm
Artem Savkin
4.3
Détails de la Version
Pays de l'Éditeur | US |
Date de Sortie dans le Pays | 2023-12-13 |
Catégories | Developer Tools |
Pays / Régions | US |
Site Web du Développeur | Artem Savkin |
URL de Support | Artem Savkin |
Évaluation du Contenu | 4+ |
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
# Inferences
* LLaMA
* GPTNeoX
* Replit
* GPT2 + Cerebras
* Starcoder(Santacoder)
* RWKV
* Falcon
* MPT
* Bloom
* StableLM-3b-4e1t
* Qwen
* Gemma
* Phi
* Mamba
* Others
# Multimodal
* LLaVA 1.5 models
* Obsidian
* Bunny
* 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)
* Locally Typical Sampling
* Mirostat
* Greedy
* Grammar
Download LLM Farm

Not Available
Évaluation Moyenne
57
Répartition des Évaluations
Avis Sélectionnés
Par Not important man
2024-08-10
Version
I think it's overall pretty good! However, I'm not a fan of the animal icons for every conversation. I believe using regular icons or even having the option to have no icon at all would attract more users to the app. Additionally, it would be great to have a "new conversation" button in the menu instead of creating a duplicate conversation each time which just made the title become longer and longer Also, maybe using AI to generate titles like ChatGPT does is great. Lastly, it would be awesome if the markdown format could be displayed during the generation process instead of after it's done. that would be awesome 👍 Anyway, thank you very much for this app!
Par Feeling defrauded
2024-02-21
Version
This app looks pretty promising, but it’s a little bit daunting to someone who’s not as familiar with setting up LLMs. For example, how do you download the LLMs and where do you go to get them? Which alarms are likely to work? It might be a good idea to include specific LLMs that have been tested on which devices. Some sort of tutorial or instructions would be really useful.
Par climboy
2024-08-20
Version
offline_functionalityReally like this app after trying it out. I can see in the preview images that can send pictures to llm, but I couldn't find the plus sign at the bottom left corner on my own phone. How does it works? The download of models will be terminated when the phone screen is off. It would be even more perfect if it could run in the background and share computing power services with other users on the local network through an API. Very good!
Captures d'Écran



