yam-peleg commited on
Commit
c4eb87a
1 Parent(s): dd6c080

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -4
README.md CHANGED
@@ -25,14 +25,17 @@ This format must be strictly respected, otherwise the model will generate sub-op
25
  <bos><start_of_turn>user
26
  Write a hello world program<end_of_turn>
27
  <start_of_turn>model
28
- Here is a simple hellow world program<end_of_turn>
29
- <eos>
30
  ```
31
 
32
- Each turn is preceded by a <start_of_turn> delimiter and then the role of the entity (either user, for content supplied by the user, or model for LLM responses). Turns finish with the <end_of_turn> token.
 
 
 
 
33
  You can follow this format to build the prompt manually, if you need to do it without the tokenizer's chat template.
34
 
35
- A simple example:
36
 
37
  ```python
38
  from transformers import AutoTokenizer, AutoModelForCausalLM
 
25
  <bos><start_of_turn>user
26
  Write a hello world program<end_of_turn>
27
  <start_of_turn>model
28
+ Here is a simple hellow world program<end_of_turn><eos>
 
29
  ```
30
 
31
+ - The conversation starts with `<bos>`.
32
+ - Each turn is preceded by a `<start_of_turn>` delimiter and then the role of the entity (`user` or `model`).
33
+ - Turns finish with the `<end_of_turn>` token.
34
+ - Conversation finish with the `<eos>` token.
35
+
36
  You can follow this format to build the prompt manually, if you need to do it without the tokenizer's chat template.
37
 
38
+ A simple example using the tokenizer's chat template:
39
 
40
  ```python
41
  from transformers import AutoTokenizer, AutoModelForCausalLM