Update README.md

README.md

@@ -27,6 +27,32 @@ KORANI is derived from GORANI, a project within llama2 that experiments with the
 <br>
 
 ## Template
+Instruction model
+```
+### System:
+{{ System prompt }}
+
+### User:
+{{ New user input }}
+
+### Assistant:
+{Assistant}
+```
+
+Chat model
+```
+<s>[INST] <<SYS>>
+{{ System prompt }}
+<</SYS>>
+
+{{ New user message }} [/INST]
+```
+
+<details>
+  <summary> Templates </summary>
+
+
+#### Instruct model template
 For safety, I used the default system message from Llama-2. But if a system message is specified in any datasets, I use that content.
 ```python
 ### System:
@@ -38,12 +64,24 @@ For safety, I used the default system message from Llama-2. But if a system mess
 ### Input:
 {{ Optional additional user input }}
 
-### Response:
+### Assistant:
 {{ New assistant answer }}
 ```
 
 need to be converted to
 
+```
+### System:
+{{ System prompt }}
+
+### User:
+{{ New user input }}
+
+### Assistant:
+{Assistant}
+```
+
+## Chat model template
 
 ```
 # https://github.com/huggingface/blog/blob/main/llama2.md#how-to-prompt-llama-2
@@ -88,6 +126,50 @@ If the sentence does not fall within these categories, is safe and does not need
 """
 ```
 
+The context-dialogue refers to the system prompt I suppose, and in this case we have N samples:
+
+```
+[SYSTEM: ](SYSTEM: Act as if you were Napoleon who like playing cricket.
+USER: <user_msg_1>
+ASSISTANT: <reply_1>
+```
+
+```
+[SYSTEM: ](SYSTEM: Act as if you were Napoleon who like playing cricket.
+USER:
+ASSISTANT:
+USER:
+ASSISTANT:
+```
+
+```
+[SYSTEM: ](SYSTEM: Act as if you were Napoleon who like playing cricket.
+USER: <user_msg_1>
+ASSISTANT: <reply_1>
+USER: <user_msg_2>
+ASSISTANT: <reply_2>
+...
+USER: <user_msg_N>
+ASSISTANT: <reply_N>
+```
+For each sample S, at training time, we pass the context:
+
+```
+[SYSTEM: ](SYSTEM: Act as if you were Napoleon who like playing cricket.
+USER: <user_msg_1>
+ASSISTANT: <reply_1>
+USER: <user_msg_2>
+ASSISTANT: <reply_2>
+...
+USER: <user_msg_S-1>
+ASSISTANT: <reply_S-1>
+USER: <user_msg_S>
+```
+And we train the probabilities on ASSISTANT: <reply_S>: the loss is zeroed out for all tokens before, then you compute cross-entropy between ground-truth (the actual <reply_S>) and the predicted tokens P(t>k|t0, ..., tk) where k is the length of the sequence
+
+</details>
+
+
 ## Update
 - Since we cannot control resources, we will record the schedule retrospectively.