Projects using Monster API
🌟 Discover Seamless Innovation with Monster API 🌟
Explore the diverse capabilities of MonsterAPI platform to build Generative AI applications.
From creating interactive coding aides to enhancing 🤖 chatbots, Monster API simplifies tasks like audio transcription, interaction enhancement, and voice-to-text conversion.
Experiment freely and elevate your projects effortlessly using Monster API. 🛠️
Monster API Projects
Auto Blogger with Monster API
Date added: December 27, 2023
AI Blogger - Input few keywords and the AI will generate high-quality blogs with title, description, and images
APIs: Zephyr 7B, SDXL
Zephyr LLM with RAG
Date added: December 7, 2023
Query an LLM like Zephyr 7B with embeddings to answer data questions using RAG.
APIs: Zephyr 7B, RAG
Voice Coding Assistant
Date added: November 22, 2023
Convert speech to text, Generate code
APIs: Whisper, Code-llama
AI Photo Generation 🤯
Date added: November 16, 2023
Convert voice to text, Finetune prompt, Get images
APIs: Whisper, Zephyr, SDXL
Audio Transcription 🎶
Date added: October 26, 2023
🗨 Effortlessly transcribe audio using Monster API's Python pip package with Whisper.
APIs: Whisper
Conversational Assistant 💬
Date added: October 17, 2023
🤖 Incorporate Whisper for speech-to-text, Falcon for intelligent responses, and Bark for audio responses.
APIs: Whisper, Falcon, Bark
Demo Notebooks for using Monster Deploy:
Serve LLMs as private API endpoints - Optimised for higher throughput at lower cost.
| Model | Details | Notebook |
|---|---|---|
| Nous Hermes 2 Mixtral 8x7B DPO | Deployed on A6000 48GB |  |
| Mixtral 8x7B LLM | Deployed on A6000 48GB | |
| Tiny-LLaMa 1.1B LLM | Deployed on A5000 24GB | |
| HuggingFaceH4/zephyr-7b-beta | Without LoRA Adapter | |
| codellama/CodeLlama-7b-hf | Huggingface LoRA Adapter qblocks/codellama7b_codealpaca20k | |
| meta-llama/Llama-2-13b-hf | Huggingface LoRA adapter IlyaGusev/saiga2_13b_lora | |
| codefuse-ai/CodeFuse-CodeLlama-34B | LoRA adapter infused into basemodel deployed on 1xA100-80GB | |
| teknium/OpenHermes-2.5-Mistral-7B | Without LoRA Adapter deployed on A5000 24GB | |
| qblocks/mistral_7b_norobots | PEFT Private Deployment / On Local Hardware | |
| Monster deploy models | Updated quick serve notebook for launching and querying monster deploy models | |
| Microsoft Phi-2 | Deployed on A4000/V100 16GB | |
Updated 18 days ago