Argus · AI Engineering

Fine-tune Llama 3 8B on your data · deploy on Vertex AI · wrap with FastAPI

What You Get

• Domain-specific fine-tuned Llama 3 8B via PEFT/LoRA
• Google Vertex AI deployment — scalable, production-ready endpoint
• FastAPI wrapper with auth, rate-limit, and OpenAPI docs
• LangChain RAG pipeline (STANDARD+) — retrieval over your documents
• Full source code + Dockerfile + deployment guide

Sample Output

POST /v1/chat -> 200 OK  model: argus-llama3-8b-finetuned-v1  latency: 312ms

Stack

How to Order

Order on Fiverr - Argus Intelligence · From $180 · 48h delivery

License

MIT © Argus Intelligence · marcosantcs