Full text tutorial with code (requires MLExpert Pro): www.mlexpert.io/bootcamp/depl...
You have a fine-tuned model (with LoRA adapter) to deploy as a REST API? In this video, we'll merge a LoRA adapter with a base model and upload it (with a tokenizer) to HuggingFace Hub. We'll build a REST API with FastAPI and deploy it as a Docker container.
Model on HuggingFace Hub: huggingface.co/curiousily/tin...
HuggingFace Space: huggingface.co/spaces/curious...
API Docs: curiousily-tiny-crypto-sentim...
AI Bootcamp (in preview): www.mlexpert.io/membership
Discord: / discord
Subscribe: bit.ly/venelin-subscribe
GitHub repository: github.com/curiousily/Get-Thi...
00:00 - Intro
00:36 - Text tutorial on MLExpert
00:56 - Merge LoRA adapter with base model
05:01 - Push the model to HuggingFace Hub
06:46 - Test the model from the HuggingFace Hub
09:45 - Rest API with FastAPI
14:36 - Dockerfile
15:45 - Create a HuggingFace Space for Docker
17:33 - Test the deployed Rest API
19:05 - Conclusion
Join this channel to get access to the perks and support my work:
/ @venelin_valkov
#artificialintelligence #sentimentanalysis #llm #docker #llama2 #chatgpt #gpt4 #python #chatbot
Негізгі бет Deploy (Tiny) LLM to Production: Merge Lora Adapter, Push to HF Hub, Rest API with FastAPI & Docker
Пікірлер: 2