update readme
Browse files
README.md
CHANGED
@@ -2,10 +2,26 @@
|
|
2 |
language:
|
3 |
- ru
|
4 |
---
|
5 |
-
# T-lite-instruct-0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
|
7 |
Detailed model card’s coming soon…
|
8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
## 👨💻 Examples of usage
|
10 |
|
11 |
|
@@ -14,9 +30,13 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
14 |
import torch
|
15 |
torch.manual_seed(42)
|
16 |
|
17 |
-
model_name = "t-
|
18 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name
|
19 |
-
model = AutoModelForCausalLM.from_pretrained(
|
|
|
|
|
|
|
|
|
20 |
|
21 |
prompt = "Напиши стих про машинное обучение"
|
22 |
messages = [
|
|
|
2 |
language:
|
3 |
- ru
|
4 |
---
|
5 |
+
# T-lite-instruct-1.0
|
6 |
+
|
7 |
+
**🚨 T-lite is designed for further fine-tuning and is not intended as a ready-to-use conversational assistant. Users are advised to exercise caution and are responsible for any additional training and oversight required to ensure the model's responses meet acceptable ethical and safety standards. The responsibility for incorporating this model into industrial or commercial solutions lies entirely with those who choose to deploy it.**
|
8 |
+
|
9 |
+
|
10 |
+
## Description
|
11 |
+
|
12 |
+
T-lite-instruct-0.1 was trained in bf16.
|
13 |
|
14 |
Detailed model card’s coming soon…
|
15 |
|
16 |
+
### 📚 Dataset
|
17 |
+
|
18 |
+
Detailed model card’s coming soon…
|
19 |
+
|
20 |
+
## 📊 Benchmarks
|
21 |
+
|
22 |
+
Detailed model card’s coming soon…
|
23 |
+
Here we present the results of T-lite-instruct-1.0 on automatic benchmarks.
|
24 |
+
|
25 |
## 👨💻 Examples of usage
|
26 |
|
27 |
|
|
|
30 |
import torch
|
31 |
torch.manual_seed(42)
|
32 |
|
33 |
+
model_name = "t-tech/T-lite-it-1.0"
|
34 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
35 |
+
model = AutoModelForCausalLM.from_pretrained(
|
36 |
+
model_name,
|
37 |
+
torch_dtype="auto",
|
38 |
+
device_map="auto"
|
39 |
+
)
|
40 |
|
41 |
prompt = "Напиши стих про машинное обучение"
|
42 |
messages = [
|