Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
license: cc-by-nc-sa-4.0
|
6 |
+
datasets:
|
7 |
+
- databricks/databricks-dolly-15k
|
8 |
+
- kyujinpy/KOR-OpenOrca-Platypus-v3
|
9 |
+
---
|
10 |
+
|
11 |
+
**Input** Models input text only.
|
12 |
+
|
13 |
+
**Output** Models generate text only.
|
14 |
+
|
15 |
+
**Base Model** [beomi/Yi-Ko-6B](https://huggingface.co/beomi/Yi-Ko-6B)
|
16 |
+
|
17 |
+
# Implementation Code
|
18 |
+
```python
|
19 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
20 |
+
import torch
|
21 |
+
repo = "ifuseok/yi-ko-playtus-instruct-v0.2"
|
22 |
+
OpenOrca = AutoModelForCausalLM.from_pretrained(
|
23 |
+
repo,
|
24 |
+
return_dict=True,
|
25 |
+
torch_dtype=torch.float16,
|
26 |
+
device_map='auto'
|
27 |
+
)
|
28 |
+
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
|
29 |
+
```
|
30 |
+
|
31 |
+
# Prompt Example
|
32 |
+
<|system|>
|
33 |
+
μμ€ν
λ©μμ§ μ
λλ€. <|endoftext|>
|
34 |
+
<|user|>
|
35 |
+
μ μ μ
λλ€.<|endoftext|>
|
36 |
+
<|assistant|>
|
37 |
+
μ΄μμ€ν΄νΈ μ
λλ€.<|endoftext|>
|