cognitivess
commited on
Commit
•
57ddfde
1
Parent(s):
78fcf7e
Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,7 @@
|
|
5 |
To use this model, first install the custom package:
|
6 |
|
7 |
```bash
|
|
|
8 |
!pip install bitsandbytes accelerate
|
9 |
!pip install git+https://huggingface.co/CognitivessAI/cognitivess
|
10 |
```
|
@@ -12,6 +13,7 @@ To use this model, first install the custom package:
|
|
12 |
Then, you can use the model like this:
|
13 |
|
14 |
```python
|
|
|
15 |
# Import necessary libraries
|
16 |
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
17 |
import torch
|
@@ -39,6 +41,7 @@ config.quantization_config = quantization_config
|
|
39 |
model = CognitivessForCausalLM.from_pretrained(
|
40 |
"CognitivessAI/cognitivess",
|
41 |
config=config,
|
|
|
42 |
device_map="auto"
|
43 |
)
|
44 |
|
|
|
5 |
To use this model, first install the custom package:
|
6 |
|
7 |
```bash
|
8 |
+
# Install required packages
|
9 |
!pip install bitsandbytes accelerate
|
10 |
!pip install git+https://huggingface.co/CognitivessAI/cognitivess
|
11 |
```
|
|
|
13 |
Then, you can use the model like this:
|
14 |
|
15 |
```python
|
16 |
+
|
17 |
# Import necessary libraries
|
18 |
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
19 |
import torch
|
|
|
41 |
model = CognitivessForCausalLM.from_pretrained(
|
42 |
"CognitivessAI/cognitivess",
|
43 |
config=config,
|
44 |
+
quantization_config=quantization_config,
|
45 |
device_map="auto"
|
46 |
)
|
47 |
|