Update space
Browse files
README.md
CHANGED
|
@@ -7,4 +7,27 @@ sdk: gradio
|
|
| 7 |
sdk_version: 4.19.2
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
sdk_version: 4.19.2
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
python_version: "3.10"
|
| 11 |
+
cuda: "11.8"
|
| 12 |
+
license: "mit"
|
| 13 |
+
duplicated_from: unsloth/Llama-3.2-3B-Instruct-bnb-4bit
|
| 14 |
+
models:
|
| 15 |
+
- unsloth/Llama-3.2-3B-Instruct-bnb-4bit
|
| 16 |
+
- emeses/lab2_model
|
| 17 |
+
tags:
|
| 18 |
+
- llama
|
| 19 |
+
- chat
|
| 20 |
+
- gradio
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# LLaMA Chat Interface
|
| 24 |
+
|
| 25 |
+
A chat interface using fine-tuned LLaMA 3.2B model.
|
| 26 |
+
|
| 27 |
+
## Features
|
| 28 |
+
- 4-bit quantization for efficient inference
|
| 29 |
+
- Adjustable generation parameters
|
| 30 |
+
- User-friendly chat interface
|
| 31 |
+
|
| 32 |
+
## Usage
|
| 33 |
+
Just start typing in the chat box to interact with the model.
|