hyunjae commited on
Commit
25414de
β€’
1 Parent(s): 658a043

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -28
README.md CHANGED
@@ -6,32 +6,6 @@ pipeline_tag: text-generation
6
  ---
7
 
8
 
9
- - base_model: polyglot-ko-3.8b1
10
  - train_data: 12 instruction fine-tuned dataset
11
- - train method: SFT
12
-
13
-
14
- ```python
15
- from transformers import AutoModelForCausalLM, AutoTokenizer
16
-
17
- device = "cuda" # the device to load the model onto
18
-
19
- model = AutoModelForCausalLM.from_pretrained("hyunjae/polyglot-ko-3.8b-total")
20
- tokenizer = AutoTokenizer.from_pretrained("hyunjae/polyglot-ko-3.8b-total")
21
-
22
- messages = [
23
- {"role": "system", "content": "당신은 μ‚¬λžŒλ“€μ΄ 정보λ₯Ό 찾을 수 μžˆλ„λ‘ λ„μ™€μ£ΌλŠ” 인곡지λŠ₯ λΉ„μ„œμž…λ‹ˆλ‹€."},
24
- {"role": "user", "content": "λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ–΄λ””μ•Ό?"},
25
- {"role": "assistant", "content": "λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ„œμšΈμž…λ‹ˆλ‹€."},
26
- {"role": "user", "content": "μ„œμšΈ μΈκ΅¬λŠ” 총 λͺ‡ λͺ…이야?"}
27
- ]
28
-
29
- encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
30
-
31
- model_inputs = encodeds.to(device)
32
- model.to(device)
33
-
34
- generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
35
- decoded = tokenizer.batch_decode(generated_ids)
36
- print(decoded[0])
37
- ```
 
6
  ---
7
 
8
 
9
+ - base_model: polyglot-ko-3.8b
10
  - train_data: 12 instruction fine-tuned dataset
11
+ - train method: SFT