Mukul Rayana commited on
Revise project description in Readme.MD
Browse filesUpdated the project description to clarify features and capabilities.
Readme.MD
CHANGED
|
@@ -8,7 +8,7 @@ A full end-to-end LLMOps serving stack — from a QLoRA fine-tuned model running
|
|
| 8 |
|
| 9 |
---
|
| 10 |
|
| 11 |
-
##
|
| 12 |
|
| 13 |
Most LLM projects stop at inference. This one goes further:
|
| 14 |
|
|
@@ -17,6 +17,7 @@ Most LLM projects stop at inference. This one goes further:
|
|
| 17 |
- **Serving layer** — FastAPI with async lifespan model loading, typed Pydantic request/response models, CORS, health check, and a clean browser UI served from the same process
|
| 18 |
- **Containerized** — Dockerfile built for slim Python 3.12, model loaded at runtime via env-configurable path (not baked in)
|
| 19 |
- **Cloud-ready** — One-shot Azure deployment via ACR + Container Apps, with Pinecone key injected as a secret
|
|
|
|
| 20 |
|
| 21 |
---
|
| 22 |
|
|
|
|
| 8 |
|
| 9 |
---
|
| 10 |
|
| 11 |
+
## About Irminsul
|
| 12 |
|
| 13 |
Most LLM projects stop at inference. This one goes further:
|
| 14 |
|
|
|
|
| 17 |
- **Serving layer** — FastAPI with async lifespan model loading, typed Pydantic request/response models, CORS, health check, and a clean browser UI served from the same process
|
| 18 |
- **Containerized** — Dockerfile built for slim Python 3.12, model loaded at runtime via env-configurable path (not baked in)
|
| 19 |
- **Cloud-ready** — One-shot Azure deployment via ACR + Container Apps, with Pinecone key injected as a secret
|
| 20 |
+
- **Intelligence-area** — Trained a personalized Corpus with Genshin Impact Game's Vast Lore and Character Builds
|
| 21 |
|
| 22 |
---
|
| 23 |
|