Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,9 @@ tags:
|
|
| 9 |
- chat
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
|
|
|
| 12 |
# Qwen2-72B-Instruct
|
| 13 |
|
| 14 |
## Introduction
|
|
|
|
| 9 |
- chat
|
| 10 |
---
|
| 11 |
|
| 12 |
+
This fits in one 3090 with 8k context using cache_4bit. Quality suffered a lot from quanting, so this might not be a good idea.
|
| 13 |
+
|
| 14 |
+
|
| 15 |
# Qwen2-72B-Instruct
|
| 16 |
|
| 17 |
## Introduction
|