haidlir commited on
Commit
76c75f7
1 Parent(s): 0873cc3

Add README.md

Browse files

- Add README.md

Files changed (1) hide show
  1. README.md +30 -0
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Notebook Info
2
+ **Reference**:
3
+ - https://huggingface.co/docs/transformers/chat_templating
4
+ - https://github.com/MicrosoftDocs/azure-docs/blob/main/articles/ai-services/openai/includes/chat-markup-language.md
5
+ - https://huggingface.co/datasets/FreedomIntelligence/alpaca-gpt4-indonesian
6
+ - https://huggingface.co/datasets/FreedomIntelligence/sharegpt-indonesian
7
+ - https://huggingface.co/datasets/FreedomIntelligence/evol-instruct-indonesian
8
+ - https://huggingface.co/datasets/jakartaresearch/indoqa
9
+
10
+
11
+ **Task**: Chat or Conversational
12
+ **Input**: User's prompt containing chat templated text in string format
13
+ **Output**: Model's generated text in string format
14
+
15
+ **Experiment**:
16
+ - Use bos and eos token to replace <|im_start|> and <|im_end|> in ChatML. (Inspired by: https://asmirnov.xyz/doppelganger)
17
+ - Penggunaan padding dan truncation sesuai max_length.
18
+ - Max length = 256, karena telah mengkonsumsi 33.7 GB.
19
+
20
+ ---
21
+ datasets:
22
+ - FreedomIntelligence/alpaca-gpt4-indonesian
23
+ - FreedomIntelligence/evol-instruct-indonesian
24
+ - FreedomIntelligence/sharegpt-indonesian
25
+ - jakartaresearch/indoqa
26
+ language:
27
+ - id
28
+ library_name: transformers
29
+ pipeline_tag: text-generation
30
+ ---