alokabhishek
commited on
Commit
•
6bc6238
1
Parent(s):
c0f2ae7
Update Readme
Browse files
README.md
CHANGED
@@ -84,6 +84,7 @@ model_name = model_id.split("/")[-1]
|
|
84 |
#### Run Inference on quantized model using chat template
|
85 |
```shell
|
86 |
# Run model
|
|
|
87 |
python examples/chat.py -m "../quant/alokabhishek/Meta-Llama-3-8B-Instruct-4.0-bpw-exl2" -mode llama3
|
88 |
```
|
89 |
|
|
|
84 |
#### Run Inference on quantized model using chat template
|
85 |
```shell
|
86 |
# Run model
|
87 |
+
# change the path of the model
|
88 |
python examples/chat.py -m "../quant/alokabhishek/Meta-Llama-3-8B-Instruct-4.0-bpw-exl2" -mode llama3
|
89 |
```
|
90 |
|