Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: gpl-3.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gpl-3.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- meta-llama/Llama-3.2-1B
|
| 7 |
+
tags:
|
| 8 |
+
- llama
|
| 9 |
+
- llama-3
|
| 10 |
+
- fine-tune
|
| 11 |
+
- personal-assistant
|
| 12 |
+
- mlops
|
| 13 |
+
- devops
|
| 14 |
+
- data-engineering
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
## 💻 Intended Use
|
| 18 |
+
|
| 19 |
+
This model is **not general-purpose**. It is designed to:
|
| 20 |
+
|
| 21 |
+
- 🧠 Answer questions about **Saptarshi Bhattacharya’s** professional background
|
| 22 |
+
- 🤖 Be integrated into a **chatbot interface** with optional **RAG support**
|
| 23 |
+
- 📜 Be served via **FastAPI** / **WebSocket** with **streaming inference** (e.g., VLLM)
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## 🔐 Limitations & Warnings
|
| 28 |
+
|
| 29 |
+
- ❗ Do **not** use this model for generic knowledge or tasks—it is domain-limited.
|
| 30 |
+
- 📅 Knowledge cut-off and factuality are limited to training data (no real-time info).
|
| 31 |
+
- 🧪 Not evaluated for bias/fairness—it is a personal assistant model.
|