Update README.md
Browse files
README.md
CHANGED
|
@@ -161,7 +161,7 @@ For systems with limited VRAM, you can load the model in 8-bit or 4-bit quantiza
|
|
| 161 |
import torch
|
| 162 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 163 |
|
| 164 |
-
tokenizer = AutoTokenizer.from_pretrained("norallm/normistral-11b")
|
| 165 |
|
| 166 |
# Load in 8-bit mode (requires ~12GB VRAM)
|
| 167 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
|
| 161 |
import torch
|
| 162 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 163 |
|
| 164 |
+
tokenizer = AutoTokenizer.from_pretrained("norallm/normistral-11b-warm")
|
| 165 |
|
| 166 |
# Load in 8-bit mode (requires ~12GB VRAM)
|
| 167 |
model = AutoModelForCausalLM.from_pretrained(
|